Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15601
    Prev
    Next
    INDEX
    Explanations

    geographical locations and demographic statistics

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

    Location descriptions and statistics

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     løpet
    -0.45
     Eintritt
    -0.42
     Bezir
    -0.40
     
    -0.36
     tallas
    -0.36
    <strong>
    -0.35
     soeur
    -0.35
     slutt
    -0.35
    def
    -0.34
     slutet
    -0.34
    POSITIVE LOGITS
     kasarigan
    1.27
    ſchaft
    1.04
     geſch
    0.99
    ðsíða
    0.94
     verſch
    0.93
    ſehen
    0.93
     beſch
    0.93
    ロウィン
    0.92
    ſicht
    0.92
    iſchen
    0.91
    Activations Density 0.021%

    No Known Activations