© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    references to the Ku Klux Klan

    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
    1276
    +0.14
    0.5%
    341
    +0.13
    0.5%
    1921
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.03
    1987
    +0.13
    0.03
    138
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.83
    StoreMessageInfo
    -0.76
    <!--
    -0.66
    <!--<
    -0.62
    FormBorderStyle
    -0.59
     للتو
    -0.59
    AndEndTag
    -0.59
     "..\..\..\
    -0.58
    resource
    -0.58
    ComponentModel
    -0.58
    POSITIVE LOGITS
     roberto
    1.27
     alberto
    1.23
     sergio
    1.15
     indestru
    1.14
     jorge
    1.13
     Augu
    1.13
     Klan
    1.12
     eduardo
    1.10
     unspeak
    1.09
     Momb
    1.08
    Activations Density 0.117%

    No Known Activations