© 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. 5481
    Prev
    Next
    INDEX
    Explanations

    statistical data and research terminology related to academic studies

    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
    184
    +0.13
    0.4%
    964
    +0.11
    0.3%
    1150
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    378
    +0.11
    0.04
    614
    +0.10
    0.04
    Negative Logits
     Mlle
    -0.88
     exé
    -0.87
     Haci
    -0.85
     Juf
    -0.84
     préc
    -0.84
     récla
    -0.84
     renfer
    -0.83
     Perci
    -0.83
     rempliss
    -0.82
     simplif
    -0.82
    POSITIVE LOGITS
    .
    0.75
    。
    0.66
    ).
    0.63
    ।
    0.63
    .</
    0.61
    ].
    0.61
     such
    0.59
    .).
    0.59
    ().
    0.58
    .)
    0.57
    Activations Density 0.518%

    No Known Activations