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. 747
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and results reporting

    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
    1577
    +0.24
    0.9%
    1343
    +0.23
    0.9%
    599
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.24
    0.11
    1343
    +0.23
    0.11
    845
    +0.08
    0.05
    Negative Logits
    <bos>
    -3.13
    /*
    -0.87
    /**
    -0.78
    <?
    -0.71
    #!/
    -0.68
     but
    -0.68
     Walkover
    -0.67
    #
    -0.67
     either
    -0.66
    CreateIndex
    -0.66
    POSITIVE LOGITS
     increa
    1.94
     affor
    1.91
     maneu
    1.90
     emphat
    1.90
     suscep
    1.87
     impra
    1.87
     resear
    1.86
     ?...
    1.84
     unlaw
    1.84
     unden
    1.80
    Activations Density 0.948%

    No Known Activations