Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 171
    Prev
    Next
    INDEX
    Explanations

    actions related to sports plays and player movements on a field or court

    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
    1577
    +0.09
    0.3%
    690
    +0.09
    0.3%
    1108
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.09
    0.07
    1038
    +0.09
    0.04
    392
    +0.09
    0.02
    Negative Logits
     alkoh
    -1.46
     kram
    -1.33
     fatis
    -1.32
     ordina
    -1.31
     fré
    -1.30
     istan
    -1.28
     lele
    -1.27
     gmbh
    -1.27
     tramont
    -1.24
     brutto
    -1.23
    POSITIVE LOGITS
     subsequently
    0.77
     eventually
    0.69
     ultimately
    0.69
     finally
    0.67
     easily
    0.66
     subsequent
    0.63
     consequently
    0.63
     safely
    0.63
     then
    0.62
     finish
    0.61
    Activations Density 0.359%

    No Known Activations