© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    information related to medical procedures and conditions, particularly bariatric surgery and obesity statistics

    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
    1741
    +0.14
    0.4%
    1253
    +0.13
    0.4%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.14
    0.03
    981
    +0.13
    0.04
    76
    +0.13
    0.03
    Negative Logits
     milf
    -0.93
     beverly
    -0.89
     chrysler
    -0.89
     pamph
    -0.87
     pixar
    -0.87
     hoody
    -0.85
     oakley
    -0.84
     gaily
    -0.84
     Secrétaire
    -0.83
     lamborghini
    -0.83
    POSITIVE LOGITS
     politics
    0.60
     economics
    0.57
     coronavirus
    0.52
     ethics
    0.51
     education
    0.50
     technology
    0.50
    曖昧さ回避
    0.50
     topics
    0.50
     article
    0.49
    politics
    0.49
    Activations Density 0.278%

    No Known Activations