© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1625
    Prev
    Next
    INDEX
    Explanations

    concepts related to educational practices and outcomes

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

    detailed lists of specific items, steps, or criteria presented in structured formats.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.44
    ὺς
    -0.43
    enterOuterAlt
    -0.38
    Hochspringen
    -0.35
    Jîn
    -0.34
    kloped
    -0.34
    bootstrapcdn
    -0.34
     colspan
    -0.32
    ὸν
    -0.32
     StringTokenizer
    -0.32
    POSITIVE LOGITS
    ;
    2.42
    ?;
    1.86
    ;");
    1.82
    !;
    1.79
    ;
    
    1.76
    ”;
    1.70
    ’;
    1.70
    »;
    1.69
    ;
    1.68
    }$;
    1.65
    Activations Density 3.897%

    No Known Activations