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. 8-GEMMASCOPE-RES-16K
    6. 15083
    Prev
    Next
    INDEX
    Explanations

    strings or references to programming or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⇑
    -0.57
     nakalista
    -0.56
     Nymp
    -0.53
    -0.49
    انجليز
    -0.49
    FTFY
    -0.49
    chaun
    -0.49
     jspb
    -0.49
     DbType
    -0.48
     Esper
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.79
     continúas
    0.69
    исленность
    0.69
     Braw
    0.67
     виправивши
    0.67
    Portail
    0.65
    import
    0.65
    DllImport
    0.64
    CGRectMake
    0.64
    RTLD
    0.64
    Activations Density 0.014%

    No Known Activations