© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2179
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
    381
    +0.20
    0.7%
    2019
    +0.19
    0.7%
    605
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.20
    0.05
    924
    +0.19
    0.05
    605
    +0.13
    0.02
    Negative Logits
    Czym
    -0.93
    Cringe
    -0.85
    Wię
    -0.81
    Zapraszamy
    -0.80
     Leurs
    -0.78
    Zalety
    -0.78
    Gdzie
    -0.78
    Dlaczego
    -0.77
    Herzlich
    -0.75
    Przyp
    -0.74
    POSITIVE LOGITS
    “
    0.76
    We
    0.71
    It
    0.71
    They
    0.69
    You
    0.69
    There
    0.68
    ,”
    0.67
    ,“
    0.66
    ”
    0.66
    If
    0.66
    Activations Density 0.130%

    No Known Activations