© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    references to data ownership and personal claims

    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
    1.0%
    1978
    +0.12
    0.4%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.29
    0.06
    460
    +0.12
    0.04
    507
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.30
    .
    -0.83
    ;
    -0.70
    ,
    -0.66
    :
    -0.64
    。
    -0.63
    ↵↵
    -0.62
     defaultstate
    -0.58
     another
    -0.57
    ↵
    -0.55
    POSITIVE LOGITS
     maneu
    1.49
     affor
    1.49
     increa
    1.46
     unlaw
    1.39
     unwarran
    1.33
     milf
    1.32
     effe
    1.28
     guarante
    1.27
     inev
    1.27
     accla
    1.27
    Activations Density 0.530%

    No Known Activations