© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1693
    Prev
    Next
    INDEX
    Explanations

    negative connotations or critiques of societal issues

    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
    +0.17
    0.6%
    453
    +0.15
    0.6%
    297
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1043
    +0.17
    0.06
    1836
    +0.15
    0.05
    613
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.85
     quitted
    -1.30
     intersper
    -1.11
     shuddered
    -1.02
     roused
    -1.01
     renounced
    -1.00
     hastened
    -0.98
     impelled
    -0.97
     saluted
    -0.96
     mustered
    -0.96
    POSITIVE LOGITS
    quarelle
    1.14
    nachron
    1.05
    dirond
    1.00
    WebElementEntity
    0.97
     credere
    0.96
     trovar
    0.95
    capulco
    0.95
    arrings
    0.94
    eronau
    0.90
    jectures
    0.88
    Activations Density 0.309%

    No Known Activations