© 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. 16-GEMMASCOPE-RES-16K
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    the start of a new text or paragraph

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

    Immediately precedes specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    code delimiters or special characters

    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
     sjø
    -0.62
    addContainerGap
    -0.60
    dhury
    -0.59
    iforme
    -0.59
    wyr
    -0.58
    melada
    -0.56
    atech
    -0.56
    uccio
    -0.55
    zaj
    -0.55
     détermin
    -0.54
    POSITIVE LOGITS
    IsMutable
    0.65
    vician
    0.62
     */;
    0.58
    ArgumentParser
    0.55
     Joss
    0.53
     juniors
    0.53
    Personendaten
    0.52
    :"-"`
    0.50
    _();
    0.50
    }>;
    0.50
    Activations Density 0.012%

    No Known Activations