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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 719
    Prev
    Next
    INDEX
    Explanations

    mentions of following or contacting individuals and organizations

    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
    +0.22
    0.9%
    1177
    +0.11
    0.4%
    856
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.22
    0.06
    1445
    +0.11
    0.06
    1799
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.16
    ⓧ
    -1.05
    <?
    -0.92
    
    
    -0.78
    /**
    -0.73
    .
    -0.71
     introduce
    -0.69
    /*
    -0.66
     in
    -0.66
     realize
    -0.66
    POSITIVE LOGITS
     accla
    2.35
     affor
    2.28
     reluct
    2.19
     maneu
    2.12
     wherea
    2.09
     emphat
    2.04
     depic
    2.03
     increa
    2.02
     inev
    2.01
     véhic
    2.00
    Activations Density 0.210%

    No Known Activations