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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 772
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating player statistics or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    1978
    +0.18
    0.7%
    1870
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.24
    0.10
    1105
    +0.18
    0.07
    776
    +0.11
    0.08
    Negative Logits
    <bos>
    -2.09
    ⓧ
    -0.91
     ddelweddau
    -0.70
    <!--
    
    -0.69
     intende
    -0.68
    ždý
    -0.64
    endwhile
    -0.64
     ***!
    -0.63
    Personendaten
    -0.63
    glMatrixMode
    -0.63
    POSITIVE LOGITS
     maneu
    1.18
     impra
    1.14
     affor
    0.99
     suscep
    0.95
     excru
    0.94
     increa
    0.91
     inev
    0.89
     🤣🤣
    0.89
     erad
    0.88
     tolerably
    0.86
    Activations Density 0.296%

    No Known Activations