© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 16145
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements indicating potential outcomes or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KeySpec
    -0.54
    UIControlState
    -0.51
    IConfiguration
    -0.48
    Demografia
    -0.47
    togram
    -0.47
     <=",
    -0.46
    ierungs
    -0.46
     Indes
    -0.46
     various
    -0.46
     Kopf
    -0.45
    POSITIVE LOGITS
    XmlAccessType
    0.62
    "]);
    
    0.62
     مُعرِّف
    0.60
    __':
    
    0.60
    migrationBuilder
    0.59
    __))
    0.58
    ++);
    0.57
    "])
    
    0.56
     endblock
    0.54
    ('');
    
    0.53
    Activations Density 0.204%

    No Known Activations