© 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. 13679
    Prev
    Next
    INDEX
    Explanations

    references to research studies and reports

    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
    284
    +0.09
    0.3%
    1055
    +0.09
    0.3%
    227
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.09
    0.04
    1055
    +0.09
    0.04
    1213
    +0.09
    0.05
    Negative Logits
     utop
    -1.05
     palet
    -0.95
     ideolog
    -0.93
     santiago
    -0.90
     logis
    -0.90
     loto
    -0.88
     sement
    -0.86
     psychiat
    -0.85
     gend
    -0.84
     palab
    -0.84
    POSITIVE LOGITS
    jątk
    0.74
    Dziękuję
    0.70
     bénéficiaire
    0.67
    durante
    0.64
    Materiał
    0.63
    jusqu
    0.63
     Dijo
    0.61
    Dzięki
    0.61
    ypeł
    0.61
    pueden
    0.61
    Activations Density 0.195%

    No Known Activations