© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2782
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to future prospects or opportunities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1137
    +0.09
    0.3%
    1805
    +0.07
    0.3%
    528
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    802
    +0.09
    0.03
    598
    +0.07
    0.03
    1137
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.23
    public
    -0.81
    .
    -0.75
    ,
    -0.75
    ↵↵
    -0.74
    private
    -0.74
     in
    -0.74
    <eos>
    -0.74
    define
    -0.73
     also
    -0.73
    POSITIVE LOGITS
     prospect
    2.43
     prospects
    2.29
     Prospects
    2.25
     scrat
    2.25
     increa
    2.22
     maneu
    2.16
     affor
    2.15
     impra
    2.15
     stockholm
    2.14
     jaya
    2.14
    Activations Density 0.111%

    No Known Activations