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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3332
    Prev
    Next
    INDEX
    Explanations

    descriptions related to a game involving goblins mining in rounds

    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
    1385
    +0.12
    0.4%
    81
    +0.12
    0.4%
    906
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1551
    +0.12
    0.04
    81
    +0.12
    0.02
    1843
    +0.12
    0.03
    Negative Logits
    autorest
    -0.50
    ffilm
    -0.47
    ביוגרפיה
    -0.47
     Mónica
    -0.46
    cún
    -0.42
    niająca
    -0.42
     suporta
    -0.42
     recentemente
    -0.42
    <()>
    -0.41
    setMinimumSize
    -0.41
    POSITIVE LOGITS
     toshiba
    0.79
     geforce
    0.76
     nokia
    0.65
    Fuckin
    0.64
     motorola
    0.64
     juf
    0.63
     uhd
    0.62
     logitech
    0.61
     gtx
    0.61
     krab
    0.61
    Activations Density 0.599%

    No Known Activations