© 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. 22-GEMMASCOPE-RES-16K
    11. 7730
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English language scripts

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

    Punctuations and symbols

    np_acts-logits-general · gemini-2.0-flash

    foreign language initial phrases

    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
     Efq
    -1.14
     ―――――
    -1.13
     RIPRODUZIONE
    -1.12
     $_"
    -1.12
     itſelf
    -1.11
    ſelves
    -1.11
     myſelf
    -1.10
     Проци
    -1.09
    neſs
    -1.09
    wiſe
    -1.09
    POSITIVE LOGITS
     |
    0.97
    <eos>
    0.91
    !
    0.89
    ?
    0.80
    ↵↵
    0.78
    .
    0.73
    ↵
    0.71
    </i>
    0.71
    </h5>
    0.71
    ↵↵↵
    0.70
    Activations Density 0.255%

    No Known Activations