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. 20-GEMMASCOPE-RES-131K
    6. 7424
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or interest in actions and information

    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_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    principalColumn
    -0.58
    StructEnd
    -0.44
    pei
    -0.44
     przecież
    -0.43
    ].)
    -0.42
    年も
    -0.42
     Johnston
    -0.40
    ecution
    -0.40
    Parcelize
    -0.40
    とも
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.49
    цездатний
    0.49
    Personendaten
    0.47
     algún
    0.45
     yourself
    0.42
     papild
    0.42
     للمعارف
    0.40
    MigrationBuilder
    0.40
     or
    0.39
    OCCURRED
    0.39
    Activations Density 0.030%

    No Known Activations