© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14851
    Prev
    Next
    INDEX
    Explanations

    proposed methodologies and their associated benefits in the context of probabilistic estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    passages in academic papers that announce and describe proposed methods and contributions, typically author statements about what they introduce, show, or provide.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases introducing or describing proposed methods, techniques, or contributions in academic/technical writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tempt
    -0.46
     Cohn
    -0.44
     horrible
    -0.43
     Roskov
    -0.43
     temptation
    -0.43
    fiets
    -0.42
     wipe
    -0.42
    postIndex
    -0.42
    Dry
    -0.41
     Dry
    -0.41
    POSITIVE LOGITS
     approach
    0.54
    approach
    0.43
     integrated
    0.40
     improved
    0.40
     propuesta
    0.39
     proposed
    0.39
    conceito
    0.39
    WebElementEntity
    0.39
     unprecedented
    0.39
     mahdol
    0.38
    Activations Density 0.956%

    No Known Activations