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. 6-RES-JB
    6. 6811
    Prev
    Next
    INDEX
    Explanations

    instances of text related to creating or customizing content

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    1.4%
    82
    +0.09
    0.6%
    2011
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1381
    +0.23
    0.05
    1194
    +0.09
    0.05
    30
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.44
    ⓧ
    -0.70
    /***
    
    -0.70
    #![
    -0.65
    public
    -0.60
     admit
    -0.57
    beans
    -0.57
     cooperate
    -0.56
     продъл
    -0.56
     held
    -0.55
    POSITIVE LOGITS
     maroc
    1.48
     increa
    1.46
     Minang
    1.45
     lele
    1.45
     affor
    1.45
     bandung
    1.43
     napoli
    1.41
     stockholm
    1.40
     wien
    1.40
     accla
    1.40
    Activations Density 0.238%

    No Known Activations