Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 3092
    Prev
    Next
    INDEX
    Explanations

    the importance and procedure of formatting and referencing in academic papers

    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
    hasMoreElements
    -0.65
     surla
    -0.65
     ligiloj
    -0.64
    IsContent
    -0.63
     BitmapFactory
    -0.61
    BitmapFactory
    -0.57
    ColumnInfo
    -0.57
    ihnachts
    -0.57
    adaptiveStyles
    -0.54
     Triassic
    -0.54
    POSITIVE LOGITS
     citation
    0.93
     cite
    0.83
     cited
    0.81
     citations
    0.81
     citing
    0.76
     APA
    0.73
     Citation
    0.72
     CITED
    0.71
     cit
    0.69
     format
    0.68
    Activations Density 0.377%

    No Known Activations