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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11878
    Prev
    Next
    INDEX
    Explanations

    specific terms related to legal and regulatory contexts identifying children and their circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyCulture
    -0.61
     zijne
    -0.57
     OMITBAD
    -0.57
     idéia
    -0.53
    mergeFrom
    -0.52
     Administrativna
    -0.52
     surla
    -0.52
     mijne
    -0.49
     sociala
    -0.49
     direta
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.62
     typelib
    0.45
    évaluateur
    0.41
     CURIAM
    0.35
    RegressionTest
    0.34
    例文帳に追加
    0.32
    ólogos
    0.31
    FTFY
    0.31
    obacz
    0.30
     Hause
    0.30
    Activations Density 0.794%

    No Known Activations