© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    statements about activities or plans individuals are interested in or excited about

    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
    303
    +0.10
    0.3%
    1921
    +0.09
    0.3%
    1856
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.10
    0.06
    1921
    +0.09
    0.05
    549
    +0.08
    0.04
    Negative Logits
     kram
    -0.92
     logis
    -0.81
     tyn
    -0.77
     maske
    -0.74
     ananas
    -0.74
     traktor
    -0.73
     kask
    -0.72
     emphat
    -0.71
     hek
    -0.71
     stoff
    -0.70
    POSITIVE LOGITS
     récla
    0.67
     since
    0.66
     lately
    0.66
    depuis
    0.59
     étu
    0.58
     surpl
    0.58
    since
    0.58
     SINCE
    0.58
     steadily
    0.57
     manquer
    0.56
    Activations Density 0.302%

    No Known Activations