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. 12-GEMMASCOPE-RES-16K
    6. 15343
    Prev
    Next
    INDEX
    Explanations

    references to struggles and the concept of persistence despite challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.58
    Portale
    -0.50
    dataclass
    -0.49
    WithIdentifier
    -0.48
    BufferException
    -0.46
    OGND
    -0.44
     uova
    -0.44
    ={({
    -0.44
    RenderAtEndOf
    -0.43
     angolo
    -0.43
    POSITIVE LOGITS
     also
    1.13
     alfo
    0.91
    also
    0.87
     همچنین
    0.83
    writeFieldEnd
    0.80
     furthermore
    0.80
     moreover
    0.79
     также
    0.77
    Also
    0.75
     também
    0.75
    Activations Density 0.900%

    No Known Activations