© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    verbs related to progress or accomplishment

    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
    690
    +0.14
    0.4%
    405
    +0.10
    0.3%
    1392
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.14
    0.04
    1413
    +0.10
    0.04
    1493
    +0.09
    0.04
    Negative Logits
    <bos>
    -0.74
    OA
    -0.47
     dépasse
    -0.43
     ולה
    -0.42
    OutOfBounds
    -0.41
     ferait
    -0.40
     pourra
    -0.40
    ROWS
    -0.39
     restera
    -0.39
    Your
    -0.38
    POSITIVE LOGITS
     AppBundle
    0.71
     corsair
    0.68
     maneu
    0.68
     hanggang
    0.65
     outlander
    0.64
     reft
    0.63
     hilux
    0.62
     ļ
    0.61
    Біографія
    0.61
     milf
    0.61
    Activations Density 0.696%

    No Known Activations