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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13070
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and movements that involve hands or physical objects

    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
    1314
    +0.10
    0.3%
    1129
    +0.10
    0.3%
    1438
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1038
    +0.10
    0.05
    1823
    +0.10
    0.04
    678
    +0.10
    0.06
    Negative Logits
     milf
    -0.79
     madonna
    -0.77
     caucasian
    -0.74
     perfet
    -0.69
     fey
    -0.68
     hobbit
    -0.67
     kraken
    -0.67
     cuck
    -0.66
     disagre
    -0.65
     hentai
    -0.65
    POSITIVE LOGITS
     ļ
    0.54
     accordingly
    0.54
    囗
    0.53
    رشف
    0.51
     ويكيميديا
    0.50
    BeanUtils
    0.50
     moze
    0.49
     impon
    0.49
     himo
    0.49
     lapto
    0.49
    Activations Density 0.608%

    No Known Activations