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. 0-RES-JB
    6. 19
    Prev
    Next
    INDEX
    Explanations

    mentions of national relevance or distribution

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.07
    0.3%
    262
    +0.06
    0.2%
    2011
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.07
    0.04
    1881
    +0.06
    0.03
    35
    +0.05
    0.03
    Negative Logits
    <bos>
    -0.82
    public
    -0.75
    //{
    
    -0.69
    switch
    -0.68
     pay
    -0.66
     void
    -0.66
     solve
    -0.66
     send
    -0.65
     take
    -0.65
     connect
    -0.64
    POSITIVE LOGITS
     affor
    2.17
     increa
    2.15
     maneu
    2.12
     fortn
    2.09
     accla
    2.07
     disagre
    2.03
     wherea
    2.03
     stockholm
    2.02
     Juf
    2.01
     strick
    1.96
    Activations Density 0.098%

    No Known Activations