© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5840
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and transformation in challenging circumstances

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

    grammatical constructions involving "way" and related linguistic patterns that describe manner or method.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    PARATUS
    -0.49
     cromado
    -0.47
     surla
    -0.46
    ußt
    -0.46
     almohada
    -0.46
     fotográfica
    -0.46
    ulipas
    -0.46
    riwal
    -0.44
     bajos
    -0.44
    WaitGroup
    -0.43
    POSITIVE LOGITS
     ISNI
    0.47
    HasAnnotation
    0.46
    SharedDtor
    0.44
    toMatchSnapshot
    0.44
     something
    0.44
    IntoConstraints
    0.44
     probably
    0.43
     rarely
    0.41
    RoutingModule
    0.41
     never
    0.40
    Activations Density 0.283%

    No Known Activations