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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24057
    Prev
    Next
    INDEX
    Explanations

    sections marked with summary comments

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

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.75
     betweenstory
    -0.75
    :✨
    -0.75
    ftagPool
    -0.69
    bootstrapcdn
    -0.68
    ----</
    -0.67
     IFTT
    -0.67
     oprot
    -0.66
    évaluateur
    -0.66
     Meksiku
    -0.66
    POSITIVE LOGITS
    __':
    
    0.35
    melte
    0.35
    ']").
    0.35
    }');
    0.33
    "]').
    0.32
    }]$
    0.31
    }],
    0.31
    "];
    
    0.31
    GOTREF
    0.30
    ',{
    0.29
    Activations Density 0.000%

    No Known Activations