© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13217
    Prev
    Next
    INDEX
    Explanations

    instances where someone takes authoritative action

    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
    1984
    +0.13
    0.4%
    687
    +0.12
    0.4%
    1446
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.13
    0.06
    1984
    +0.12
    0.06
    331
    +0.10
    0.05
    Negative Logits
     gaily
    -0.93
     apprehen
    -0.91
     nobly
    -0.90
     vainly
    -0.89
     ineffec
    -0.89
     inconce
    -0.87
     unspeak
    -0.84
     tolerably
    -0.81
     disagre
    -0.78
     disgra
    -0.77
    POSITIVE LOGITS
     WITH
    0.69
    WITH
    0.64
    pertise
    0.63
    with
    0.61
     sentito
    0.58
    sightly
    0.58
     gusto
    0.57
     soggior
    0.56
     skimage
    0.56
    With
    0.56
    Activations Density 0.218%

    No Known Activations