© 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. 7622
    Prev
    Next
    INDEX
    Explanations

    information related to brain activity and function, particularly in the context of physical activity or sports

    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
    394
    +0.12
    0.4%
    906
    +0.10
    0.3%
    605
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.12
    0.07
    1496
    +0.10
    0.04
    1419
    +0.09
    0.04
    Negative Logits
     wien
    -1.39
     mef
    -1.37
     dispen
    -1.36
     lele
    -1.35
     socie
    -1.34
     Juf
    -1.34
     dises
    -1.33
     hina
    -1.31
     meis
    -1.30
     ivi
    -1.29
    POSITIVE LOGITS
     effortlessly
    0.74
     effortless
    0.71
     seamlessly
    0.59
     elegance
    0.58
     skill
    0.58
     seamless
    0.57
     brilliance
    0.57
     génie
    0.55
    stdarg
    0.54
     flawless
    0.54
    Activations Density 0.639%

    No Known Activations