© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    various contact information details and actions like sending letters or care packages

    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
    +0.16
    0.8%
    1842
    +0.06
    0.3%
    1177
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.16
    -0.10
    1842
    +0.06
    0.01
    50
    +0.06
    0.21
    Negative Logits
    <bos>
    -2.32
    <?
    -0.97
    </tbody>
    -0.94
    public
    -0.93
    ⓧ
    -0.91
    Vegeu
    -0.90
    /*
    -0.88
    /**
    -0.88
    addComponent
    -0.87
    ValueGenerated
    -0.86
    POSITIVE LOGITS
     maneu
    3.78
     increa
    3.63
     affor
    3.63
     reluct
    3.55
     disagre
    3.52
     shenan
    3.43
     depic
    3.42
     impra
    3.42
     scrat
    3.30
     accla
    3.27
    Activations Density 7.601%

    No Known Activations