© 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. 2585
    Prev
    Next
    INDEX
    Explanations

    information related to a specific software or company named Res

    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
    1590
    +0.08
    0.3%
    50
    +0.08
    0.3%
    501
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.08
    0.03
    1590
    +0.08
    0.03
    765
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.60
    //{
    -0.73
    public
    -0.73
    addComponent
    -0.72
    inline
    -0.66
    //{
    -0.66
    interface
    -0.66
    createElement
    -0.65
    País
    -0.65
    itemize
    -0.65
    POSITIVE LOGITS
     maneu
    2.21
     disagre
    2.15
     increa
    2.14
     affor
    2.09
     milf
    2.08
     squa
    2.08
     fuf
    2.07
     emphat
    2.06
     resear
    2.05
     strick
    2.03
    Activations Density 0.141%

    No Known Activations