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. 22-GEMMASCOPE-RES-16K
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    words associated with technical instructions and specifications

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    mathematical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -1.06
     الحره
    -0.98
     Cæsar
    -0.95
     Efq
    -0.95
    DoubleQuotes
    -0.94
    KommentareTeilen
    -0.94
    ArgsConstructor
    -0.90
     itſelf
    -0.90
     ſeveral
    -0.90
     Monfieur
    -0.88
    POSITIVE LOGITS
     вами
    0.46
     fa
    0.42
    ,
    0.42
     f
    0.41
     тобой
    0.41
     c
    0.39
    giphy
    0.39
     und
    0.38
     мной
    0.37
     pro
    0.37
    Activations Density 0.032%

    No Known Activations