© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4773
    Prev
    Next
    INDEX
    Explanations

    instances of denial or counterarguments

    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
    +0.32
    1.1%
    1276
    +0.08
    0.3%
    1473
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.32
    0.05
    1507
    +0.08
    0.04
    1479
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.98
    Autoritní
    -0.63
     "..\..\..\
    -0.57
    cur
    -0.54
    raise
    -0.54
    Controllo
    -0.53
    jsii
    -0.53
    <eos>
    -0.51
    generated
    -0.51
    expandindo
    -0.51
    POSITIVE LOGITS
     accla
    1.44
     disgra
    1.41
     disagre
    1.34
     impra
    1.28
     maneu
    1.24
     reluct
    1.23
     disreg
    1.22
     apprehen
    1.20
     shenan
    1.19
     emphat
    1.18
    Activations Density 0.302%

    No Known Activations