© 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 EvalsExportsinterp-engineNEWAPI 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. 10627
    Prev
    Next
    INDEX
    Explanations

    article references with DOI numbers

    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
    1343
    +0.15
    0.4%
    924
    +0.13
    0.4%
    208
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.15
    0.02
    422
    +0.13
    0.02
    208
    +0.09
    0.02
    Negative Logits
     unspeak
    -1.49
     gaily
    -1.31
     ineffec
    -1.28
     Yugos
    -1.27
     impra
    -1.27
     sophistic
    -1.26
     disagre
    -1.25
     impractica
    -1.25
     Shakspeare
    -1.24
     vainly
    -1.24
    POSITIVE LOGITS
    <bos>
    1.43
     torba
    0.75
     fré
    0.73
     barna
    0.68
    "../
    0.66
     poud
    0.66
     biografi
    0.64
     '\\;'
    0.63
    UIAlert
    0.63
     Informações
    0.63
    Activations Density 0.027%

    No Known Activations