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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12584
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychiatric disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.73
     OMITBAD
    -0.65
    rrggbb
    -0.62
    featureID
    -0.62
    ronpa
    -0.58
    EndInit
    -0.57
    MigrationBuilder
    -0.56
    Personendaten
    -0.54
    StoryboardSegue
    -0.54
    hyrchwyd
    -0.52
    POSITIVE LOGITS
     collation
    0.57
     coll
    0.48
     search
    0.48
     compiled
    0.47
     compilation
    0.47
     review
    0.44
    summar
    0.43
     liệt
    0.42
     compile
    0.42
     compiling
    0.42
    Activations Density 1.152%

    No Known Activations