© 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. 6113
    Prev
    Next
    INDEX
    Explanations

    mentions of movement or action in the context of writing or narration

    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
    241
    +0.12
    0.4%
    1678
    +0.10
    0.3%
    289
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.12
    0.02
    241
    +0.10
    0.02
    16
    +0.10
    0.03
    Negative Logits
     jacques
    -0.67
     dedans
    -0.53
     Chapitre
    -0.52
     juventus
    -0.52
    kaç
    -0.52
     tegens
    -0.52
    labili
    -0.51
     Mère
    -0.50
     esimer
    -0.50
     Ibidem
    -0.50
    POSITIVE LOGITS
     dignité
    0.73
     bonté
    0.69
     forment
    0.68
     sagesse
    0.68
    Tó
    0.63
     affez
    0.59
     rendono
    0.59
     sembrano
    0.58
    entibus
    0.58
     réputation
    0.58
    Activations Density 0.137%

    No Known Activations