Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65958
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of lack or absence in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nor
    -0.46
    inSlope
    -0.43
    ();?>
    -0.43
    ;?>
    -0.41
    ']?>
    -0.40
     twenty
    -0.39
    getSystemService
    -0.39
    venske
    -0.39
     thirteen
    -0.38
     Nor
    -0.38
    POSITIVE LOGITS
    RefNanny
    0.50
     HasFactory
    0.47
    MigrationBuilder
    0.45
     unmute
    0.44
     always
    0.43
    akhstan
    0.43
     zwykle
    0.43
     tolerate
    0.43
     siempre
    0.43
    Mutagenicity
    0.43
    Activations Density 0.091%

    No Known Activations