© 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. 2176
    Prev
    Next
    INDEX
    Explanations

    terms related to polling, voting, and legal decisions

    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
    +0.19
    0.6%
    1870
    +0.11
    0.4%
    605
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.19
    0.07
    1870
    +0.11
    0.04
    946
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.80
     ***!
    -1.06
    InputBorder
    -1.06
    HasAnnotation
    -1.00
    HasIndex
    -0.98
    AutoScaleMode
    -0.98
    IsContent
    -0.98
    addComponent
    -0.96
    enumi
    -0.95
    HasColumnType
    -0.95
    POSITIVE LOGITS
     maneu
    2.76
     disagre
    2.62
     reluct
    2.55
     increa
    2.46
     hentai
    2.44
     shenan
    2.44
     Juf
    2.43
     affor
    2.40
     depic
    2.37
     milf
    2.37
    Activations Density 0.416%

    No Known Activations