© 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. 13238
    Prev
    Next
    INDEX
    Explanations

    suggestions for improving or providing examples in documentation

    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
    1387
    +0.13
    0.5%
    1974
    +0.13
    0.5%
    871
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1974
    +0.13
    0.07
    1387
    +0.13
    0.07
    871
    +0.12
    0.06
    Negative Logits
     poulet
    -0.82
     chèvre
    -0.76
     frambo
    -0.75
     pommes
    -0.74
     patata
    -0.73
     bakso
    -0.73
     poire
    -0.72
     churras
    -0.70
     persil
    -0.70
     bandung
    -0.69
    POSITIVE LOGITS
    can
    0.85
     can
    0.84
     contribue
    0.76
     Can
    0.73
    Can
    0.72
     CAN
    0.72
     affor
    0.69
    
    0.67
    CAN
    0.66
     be
    0.65
    Activations Density 0.241%

    No Known Activations