© 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. 40-GEMMASCOPE-RES-16K
    6. 1026
    Prev
    Next
    INDEX
    Explanations

    numerical data and their relationships in mathematical expressions or models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.44
     ſch
    -0.43
     Opiniones
    -0.42
    StoryboardSegue
    -0.40
     meditations
    -0.40
    JAKARTA
    -0.38
    migrationBuilder
    -0.37
     vPvB
    -0.37
    monials
    -0.37
     grenades
    -0.36
    POSITIVE LOGITS
     _
    0.82
    \_
    0.78
    }\\
    0.76
    _
    
    0.73
     \_
    0.73
    ...}
    0.70
    }$}
    0.70
     !_
    0.68
    '}
    0.67
    ')}
    0.66
    Activations Density 0.122%

    No Known Activations