© 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 EvalsExportsinterp-engineNEWAPI 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. 16121
    Prev
    Next
    INDEX
    Explanations

    content related to past actions or events

    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
    1023
    +0.15
    0.6%
    31
    +0.12
    0.5%
    1778
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.15
    0.11
    31
    +0.12
    0.07
    1616
    +0.12
    0.07
    Negative Logits
    <bos>
    -0.60
    OGND
    -0.55
     prét
    -0.55
     bolí
    -0.52
     zumal
    -0.52
     préc
    -0.50
     viendra
    -0.49
    Geografie
    -0.47
    opsida
    -0.47
    GRAY
    -0.45
    POSITIVE LOGITS
     unwarran
    0.80
     intersper
    0.75
     was
    0.74
     Was
    0.73
    was
    0.73
     wasnt
    0.73
     impractica
    0.72
     reft
    0.71
    Was
    0.71
     WERE
    0.70
    Activations Density 0.597%

    No Known Activations