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

    Neuronpedia

    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. 7148
    Prev
    Next
    INDEX
    Explanations

    information related to government actions and legal proceedings

    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
    2019
    +0.38
    1.4%
    1535
    +0.21
    0.8%
    381
    +0.21
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.38
    0.21
    1535
    +0.21
    0.17
    1445
    +0.21
    0.17
    Negative Logits
     bandai
    -0.91
    Czym
    -0.89
    Polecam
    -0.84
    Zapraszamy
    -0.83
    Dziękuję
    -0.82
     Darum
    -0.82
    Może
    -0.81
    Nichts
    -0.81
    Lmfao
    -0.80
    Genau
    -0.79
    POSITIVE LOGITS
    mavi
    0.80
    umum
    0.77
    However
    0.76
     Glou
    0.75
    The
    0.74
     Varan
    0.74
    But
    0.74
    This
    0.73
    Then
    0.73
     Keny
    0.72
    Activations Density 1.264%

    No Known Activations