© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14264
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to licenses and agreements

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

    Code, file paths, and licenses

    np_acts-logits-general · gemini-2.0-flash

    paths, licenses, elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.79
     […]
    -1.77
    ↵↵
    -1.44
     [...]
    -1.27
    <eos>
    -1.21
     =
    
    -1.18
    ',...
    -1.18
    ,...
    -1.15
    </h4>
    -1.11
    Показать
    -1.10
    POSITIVE LOGITS
    帖最后由
    0.49
    TextEditing
    0.48
    ☆☆☆☆
    0.47
    μβρίου
    0.46
    μιουργ
    0.45
     @"";
    0.45
     ó
    0.45
     Uint
    0.43
    viembre
    0.43
    󠁣
    0.43
    Activations Density 1.421%

    No Known Activations