© 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 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. 14736
    Prev
    Next
    INDEX
    Explanations

    sources and credits mentioned in articles

    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
    1577
    +0.10
    0.3%
    1403
    +0.09
    0.3%
    1793
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.10
    0.05
    1041
    +0.09
    0.04
    1003
    +0.08
    0.02
    Negative Logits
     hiszen
    -0.62
    utivos
    -0.59
     више
    -0.54
     توانند
    -0.54
     Italijanski
    -0.54
    archiviato
    -0.54
    DisplayMetrics
    -0.54
     along
    -0.53
     بعد
    -0.53
    برای
    -0.53
    POSITIVE LOGITS
     increa
    1.62
     encomp
    1.59
     affor
    1.55
     guarante
    1.54
     scrat
    1.53
     maneu
    1.51
     impra
    1.51
     accla
    1.48
     suscep
    1.47
     unden
    1.46
    Activations Density 0.169%

    No Known Activations