© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2813
    Prev
    Next
    INDEX
    Explanations

    information related to instructions and guides

    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
    +0.41
    2.2%
    394
    +0.14
    0.8%
    1577
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.41
    0.31
    1577
    +0.14
    0.42
    1093
    +0.14
    0.25
    Negative Logits
    <bos>
    -2.44
    <eos>
    -0.83
    public
    -0.82
    protected
    -0.70
    ⓧ
    -0.69
    @
    -0.69
    ComponentModel
    -0.68
    void
    -0.66
    ,
    -0.65
    //
    -0.65
    POSITIVE LOGITS
     accla
    2.16
     maneu
    2.12
     impra
    2.10
     Juf
    2.04
     affor
    2.03
     increa
    2.02
     inev
    1.96
     unlaw
    1.96
     reluct
    1.94
     emphat
    1.94
    Activations Density 22.587%

    No Known Activations