© 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. 14311
    Prev
    Next
    INDEX
    Explanations

    declarative statements discussing ideas and beliefs

    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
    2034
    +0.14
    0.4%
    1535
    +0.12
    0.3%
    605
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.06
    310
    +0.12
    0.04
    106
    +0.11
    0.04
    Negative Logits
     increa
    -1.45
     affor
    -1.44
     shenan
    -1.34
     emphat
    -1.32
     disagre
    -1.31
     volunte
    -1.31
     reluct
    -1.31
     accla
    -1.30
     encomp
    -1.30
     strick
    -1.29
    POSITIVE LOGITS
     whereas
    0.94
     Whereas
    0.86
    whereas
    0.83
    Whereas
    0.83
     But
    0.78
     However
    0.73
    But
    0.69
    Demografie
    0.69
    Etimología
    0.68
    but
    0.67
    Activations Density 0.314%

    No Known Activations