© 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. 7466
    Prev
    Next
    INDEX
    Explanations

    instances of fire or flames

    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
    636
    +0.12
    0.4%
    67
    +0.11
    0.4%
    1276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.04
    1565
    +0.11
    0.04
    1828
    +0.10
    0.04
    Negative Logits
     kram
    -0.77
     puto
    -0.73
     doman
    -0.71
     astu
    -0.68
     alkoh
    -0.67
     rú
    -0.67
     bascul
    -0.66
     ordina
    -0.66
     aig
    -0.66
     Öster
    -0.65
    POSITIVE LOGITS
     flames
    1.12
     flame
    1.06
     burning
    0.98
     fires
    0.94
     fire
    0.92
     burns
    0.88
     burn
    0.88
     Flames
    0.88
     burned
    0.85
    flame
    0.84
    Activations Density 0.222%

    No Known Activations