© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    references to a specific event or location followed by the words "Meets Bagel."

    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
    453
    +0.13
    0.4%
    1978
    +0.13
    0.4%
    690
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.02
    453
    +0.13
    0.04
    764
    +0.12
    0.03
    Negative Logits
     kani
    -0.72
     disagre
    -0.68
     muna
    -0.63
     bandung
    -0.63
     thut
    -0.62
     pinak
    -0.62
    <bos>
    -0.61
    iented
    -0.61
    truction
    -0.60
    ervations
    -0.60
    POSITIVE LOGITS
     Konkur
    0.74
     kosme
    0.71
     loisirs
    0.71
    Literat
    0.64
     déliv
    0.64
     profili
    0.64
     confé
    0.63
     minimalis
    0.63
    emmel
    0.62
     célé
    0.62
    Activations Density 0.126%

    No Known Activations