© 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. 12876
    Prev
    Next
    INDEX
    Explanations

    details related to medical procedures and injuries, specifically in the context of sports injuries and surgeries

    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
    184
    +0.30
    1.0%
    1967
    +0.17
    0.6%
    1842
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.30
    0.05
    1499
    +0.17
    0.06
    1904
    +0.15
    0.05
    Negative Logits
     swarovski
    -0.84
     embodi
    -0.79
     tricot
    -0.72
     napoli
    -0.68
     jacques
    -0.67
     strass
    -0.66
     broderie
    -0.66
     fluo
    -0.64
     disreg
    -0.63
     indestru
    -0.63
    POSITIVE LOGITS
     thereafter
    0.69
     NUKAT
    0.63
     PLWABN
    0.62
     later
    0.56
     then
    0.56
    ביוגרפיה
    0.56
     subsequently
    0.55
     afterwards
    0.55
     afterward
    0.53
    lccccc
    0.52
    Activations Density 0.511%

    No Known Activations