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. 11299
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective experiences and actions involving groups

    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
     tartalomajánló
    -0.68
     transférez
    -0.63
     برانيه
    -0.62
    MigrationBuilder
    -0.61
     ligiloj
    -0.59
    QMetaType
    -0.57
     BoxFit
    -0.56
    +:+
    -0.56
    saraba
    -0.56
    RegressionTest
    -0.54
    POSITIVE LOGITS
     voet
    0.38
    ้งาน
    0.35
    劲
    0.34
     BIN
    0.33
    화
    0.33
     Jansen
    0.32
    UserEntity
    0.32
    όμε
    0.32
     bandas
    0.31
     Beres
    0.31
    Activations Density 1.654%

    No Known Activations