© 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. 20-GEMMASCOPE-RES-16K
    6. 16167
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions related to matrices and equations

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

    mathematical notation and symbols in formulas, particularly parentheses and mathematical operators.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     createDate
    -0.37
    AndroidJUnit
    -0.37
     Tet
    -0.35
    NTIS
    -0.34
     mercan
    -0.34
    scriptcase
    -0.33
     vesti
    -0.32
     Arco
    -0.32
    Xna
    -0.31
     mAdapter
    -0.31
    POSITIVE LOGITS
    Hentet
    0.60
    writerow
    0.57
    ://$
    0.57
    })));
    0.55
    ]=>
    0.55
    .*")]
    0.54
     CGRectMake
    0.54
     between
    0.54
    CGRectMake
    0.54
     Zwischen
    0.52
    Activations Density 1.026%

    No Known Activations