© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    information about networking such as career advice, connections, and collaboration opportunities

    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
    +0.12
    0.5%
    1870
    +0.09
    0.4%
    1404
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.12
    0.05
    590
    +0.09
    0.05
    1484
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.94
    ുറ
    -0.79
    }{||
    -0.66
    public
    -0.61
    //
    -0.61
    MarshalTo
    -0.61
    ่
    -0.61
    lateinit
    -0.61
    ///
    -0.61
    WriteLiteral
    -0.61
    POSITIVE LOGITS
     maneu
    1.88
     fta
    1.79
     affor
    1.78
     wien
    1.77
     stockholm
    1.76
     Augu
    1.73
     Intere
    1.71
     increa
    1.70
     Juf
    1.69
     milano
    1.69
    Activations Density 0.071%

    No Known Activations