© 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. 6869
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of individuals including height, weight, and appearance features

    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
    +0.30
    1.1%
    1842
    +0.21
    0.8%
    1577
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.30
    0.04
    1842
    +0.21
    0.07
    1343
    +0.20
    0.07
    Negative Logits
     reluct
    -2.67
     maneu
    -2.60
     impra
    -2.60
     depic
    -2.57
     increa
    -2.56
     disagre
    -2.52
     encomp
    -2.50
     inev
    -2.50
     affor
    -2.49
     shenan
    -2.48
    POSITIVE LOGITS
    .
    0.61
    Ngoài
    0.61
    VersionUID
    0.61
    גרפיה
    0.61
     sowie
    0.60
     esto
    0.60
     tu
    0.60
    hysema
    0.60
    成
    0.59
    rália
    0.59
    Activations Density 0.524%

    No Known Activations