© 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. 11784
    Prev
    Next
    INDEX
    Explanations

    keywords related to news articles and 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
    1150
    +0.12
    0.4%
    2034
    +0.10
    0.3%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.12
    0.05
    1762
    +0.10
    0.04
    1429
    +0.10
    0.04
    Negative Logits
    Przyp
    -0.98
    Dziękuję
    -0.97
    źródło
    -0.93
    Dlaczego
    -0.92
    Ży
    -0.91
    Może
    -0.91
    Bardzo
    -0.91
    Pozdrawiam
    -0.90
    Wię
    -0.89
    Díky
    -0.88
    POSITIVE LOGITS
    <bos>
    0.89
     depic
    0.85
     intersper
    0.83
     attemp
    0.79
     accla
    0.79
     intermitt
    0.77
     reluct
    0.77
     resurre
    0.76
     encomp
    0.76
     maneu
    0.75
    Activations Density 0.536%

    No Known Activations