© 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. 10-RES-JB
    11. 4530
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations and policies regarding states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.1%
    198
    +0.11
    0.4%
    1129
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1129
    +0.29
    0.06
    1948
    +0.11
    0.05
    361
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.65
     himself
    -0.66
     was
    -0.63
    @
    -0.63
     is
    -0.62
     someone
    -0.60
     for
    -0.60
    //@
    -0.60
     in
    -0.59
    ⓧ
    -0.59
    POSITIVE LOGITS
     stockholm
    1.75
     Juf
    1.72
     fta
    1.66
     frankfurt
    1.61
     fep
    1.61
     hcm
    1.61
     dises
    1.59
     desir
    1.58
     accla
    1.58
     increa
    1.58
    Activations Density 0.752%

    No Known Activations