© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3060
    Prev
    Next
    INDEX
    Explanations

    references to relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subject
    -0.36
     subject
    -0.36
    SPECIFIED
    -0.36
    ByPrimaryKey
    -0.35
     quedado
    -0.34
    <bos>
    -0.34
    beren
    -0.34
    ayon
    -0.33
    ish
    -0.33
     onderwerp
    -0.32
    POSITIVE LOGITS
     relations
    0.81
     Relations
    0.78
    IsMutable
    0.71
     relation
    0.66
    出版年
    0.64
    Relations
    0.63
    relations
    0.63
    ConstraintMaker
    0.63
     RELATIONS
    0.63
     Relation
    0.61
    Activations Density 0.182%

    No Known Activations