© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    words related to crime, guilt, trials, and legal proceedings

    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
    899
    +0.14
    0.5%
    204
    +0.12
    0.4%
    860
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    899
    +0.14
    0.03
    860
    +0.12
    0.02
    204
    +0.12
    0.02
    Negative Logits
     naran
    -0.61
     bambu
    -0.59
     beren
    -0.59
     ideolog
    -0.57
     bont
    -0.57
     interessa
    -0.56
     cera
    -0.56
     protes
    -0.55
     bander
    -0.54
     doman
    -0.53
    POSITIVE LOGITS
     Guilty
    1.11
     guilty
    1.10
    guilty
    1.04
    Guilty
    1.02
     guilt
    0.93
     Guilt
    0.88
     guil
    0.63
     collège
    0.62
     bourg
    0.61
     psycopg
    0.59
    Activations Density 0.065%

    No Known Activations