© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15522
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to Android programming components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انيف
    -0.67
     HasFactory
    -0.57
    Chham
    -0.54
     kaynağından
    -0.53
    kloped
    -0.53
    IsMutable
    -0.52
    writeFieldEnd
    -0.52
     betweenstory
    -0.52
     note
    -0.52
    acaktır
    -0.52
    POSITIVE LOGITS
    кобрита
    0.64
    import
    0.64
     "..\..\
    0.60
    <?
    0.59
     Audiodateien
    0.59
    COUVER
    0.58
     Brownian
    0.57
    CGRectMake
    0.55
     "..\..\..\
    0.53
    󠁿
    0.53
    Activations Density 0.014%

    No Known Activations