© 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. 7375
    Prev
    Next
    INDEX
    Explanations

    information about products made from traditional Ethiopian blankets

    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
    1703
    +0.12
    0.4%
    50
    +0.09
    0.3%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.05
    227
    +0.09
    0.07
    736
    +0.09
    0.06
    Negative Logits
     lapto
    -0.87
     impossibile
    -0.76
     utop
    -0.71
     Bintang
    -0.70
     abbra
    -0.67
     gymnas
    -0.67
     banan
    -0.64
     musli
    -0.63
     satel
    -0.63
     gioca
    -0.63
    POSITIVE LOGITS
     reluct
    0.98
     disagre
    0.98
     Thos
    0.96
     unspeak
    0.96
     withal
    0.95
     gaily
    0.92
     Daven
    0.90
     unwarran
    0.90
     indescri
    0.88
     McLaugh
    0.87
    Activations Density 0.898%

    No Known Activations