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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7323
    Prev
    Next
    INDEX
    Explanations

    conversational expressions and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    zyż
    -0.53
     affairs
    -0.48
     lainnya
    -0.47
     Reverso
    -0.45
    ждествен
    -0.45
    mkdirs
    -0.44
    を
    -0.44
     demais
    -0.43
    deka
    -0.42
     Тогда
    -0.42
    POSITIVE LOGITS
    interopRequire
    0.80
     “
    0.74
    >--}}
    0.72
    $")
    0.71
     mergeFrom
    0.71
    viously
    0.67
    ;">
    
    0.67
     ‘
    0.65
    ,”
    0.65
    ImageContext
    0.64
    Activations Density 0.122%

    No Known Activations