© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    numeric references or citations

    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
    1967
    +0.09
    0.3%
    124
    +0.09
    0.3%
    2019
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.02
    924
    +0.09
    0.01
    312
    +0.08
    0.01
    Negative Logits
     mef
    -1.88
     pessi
    -1.86
     alre
    -1.84
     kram
    -1.82
     dises
    -1.78
     „,
    -1.76
     gend
    -1.75
     fte
    -1.75
     seiz
    -1.74
     suspic
    -1.72
    POSITIVE LOGITS
    <bos>
    1.39
    GraphicsUnit
    0.75
    ftagPool
    0.70
    textTheme
    0.69
    SneakyThrows
    0.67
    /
    0.63
     useParams
    0.63
    fromLTRB
    0.62
     sämtliche
    0.62
     makeStyles
    0.62
    Activations Density 0.015%

    No Known Activations