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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3826
    Prev
    Next
    INDEX
    Explanations

    references to famous individuals and their achievements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    764
    +0.13
    0.4%
    1177
    +0.11
    0.4%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1654
    +0.13
    0.08
    981
    +0.11
    0.08
    1177
    +0.11
    0.04
    Negative Logits
     ftu
    -0.78
     perfon
    -0.76
     ftre
    -0.74
     fuper
    -0.70
     juft
    -0.70
     unwarran
    -0.69
     fua
    -0.69
     fince
    -0.68
     defire
    -0.68
     obfer
    -0.67
    POSITIVE LOGITS
     ويكيميديا
    0.53
    Ծանոթ
    0.50
    pylab
    0.46
    neden
    0.44
    increments
    0.44
    eski
    0.43
    letten
    0.43
    autoreleasepool
    0.43
    <0xEF>
    0.42
    bastien
    0.42
    Activations Density 0.577%

    No Known Activations