© 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. 0-RES-JB
    11. 2508
    Prev
    Next
    INDEX
    Explanations

    sentences related to invitations or schedules

    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
    1047
    +0.11
    0.3%
    1921
    +0.10
    0.3%
    1548
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.03
    1120
    +0.10
    0.04
    690
    +0.09
    0.03
    Negative Logits
     would
    -0.73
     mocht
    -0.70
    か
    -0.68
     once
    -0.67
    날
    -0.67
     put
    -0.67
     might
    -0.66
    <eos>
    -0.66
     по
    -0.66
    ま
    -0.66
    POSITIVE LOGITS
    :-(
    1.88
     (−
    1.86
     overla
    1.84
     inder
    1.82
     ;-
    1.79
     effe
    1.77
     inev
    1.77
     affor
    1.76
     suscep
    1.74
     wherea
    1.74
    Activations Density 0.311%

    No Known Activations