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. 16-GEMMASCOPE-RES-16K
    6. 9140
    Prev
    Next
    INDEX
    Explanations

    terms related to versioning and configuration in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Two-letter sequences

    np_acts-logits-general · gemini-2.0-flash

    short strings often followed by parts of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.63
     Sever
    -0.61
     DOM
    -0.60
     المع
    -0.60
    ter
    -0.59
    DOM
    -0.59
    pen
    -0.57
    <strong>
    -0.57
    tered
    -0.56
    <h3>
    -0.56
    POSITIVE LOGITS
    DockStyle
    1.08
     виправивши
    1.06
    IsMutable
    0.97
    kháu
    0.93
    SharedCtor
    0.93
     betweenstory
    0.92
    rrggbb
    0.91
     beginnetje
    0.90
    AccessorTable
    0.89
    ؤلاء
    0.87
    Activations Density 1.499%

    No Known Activations