© 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. 5373
    Prev
    Next
    INDEX
    Explanations

    phrases starting with bullet points, list items, or commands

    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
    1343
    +0.12
    0.3%
    1314
    +0.10
    0.3%
    1473
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.12
    0.03
    1314
    +0.10
    0.04
    1725
    +0.10
    0.02
    Negative Logits
     ModelExpression
    -0.77
     silikon
    -0.72
     lapto
    -0.71
     kosme
    -0.70
     alkoh
    -0.69
     naran
    -0.68
     utop
    -0.68
     cabrio
    -0.67
     liev
    -0.66
     poliuret
    -0.66
    POSITIVE LOGITS
    !
    0.57
    ...
    0.52
     everywhere
    0.52
     shenan
    0.48
     always
    0.47
     ineffec
    0.47
     wherever
    0.46
    …
    0.46
     let
    0.45
    !!
    0.45
    Activations Density 0.198%

    No Known Activations