© 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. 1973
    Prev
    Next
    INDEX
    Explanations

    references to forms and documents, possibly for official or administrative purposes

    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
    1637
    +0.10
    0.3%
    1052
    +0.08
    0.2%
    1335
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.03
    1363
    +0.08
    0.03
    344
    +0.08
    0.02
    Negative Logits
    복
    -0.67
    switch
    -0.66
    public
    -0.65
     أعلام
    -0.64
    card
    -0.64
    ตรี
    -0.64
     công
    -0.63
     الاحت
    -0.63
    ซ
    -0.62
     пад
    -0.62
    POSITIVE LOGITS
     Kb
    2.28
     KB
    2.25
     kb
    2.17
     accla
    2.05
     affor
    2.03
     increa
    2.01
     embra
    1.98
     inev
    1.94
     volunte
    1.94
     reluct
    1.93
    Activations Density 0.234%

    No Known Activations