© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16338
    Prev
    Next
    INDEX
    Explanations

    JavaScript code structures associated with promises and async/await

    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
    1343
    +0.18
    0.5%
    876
    +0.14
    0.4%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1988
    +0.18
    0.03
    27
    +0.14
    0.03
    49
    +0.11
    0.03
    Negative Logits
    Ży
    -0.74
    Zgod
    -0.73
    Wię
    -0.70
    Při
    -0.68
    Ekster
    -0.65
    Hvor
    -0.65
    Před
    -0.64
    Bagi
    -0.64
    Hvem
    -0.64
    لقد
    -0.63
    POSITIVE LOGITS
     clio
    1.32
     milano
    1.30
     napoli
    1.25
     bandung
    1.20
     haup
    1.19
     doman
    1.15
     chrysler
    1.15
     lamborghini
    1.15
     vns
    1.13
     fatis
    1.13
    Activations Density 0.055%

    No Known Activations