© 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. 13831
    Prev
    Next
    INDEX
    Explanations

    first-person plural pronouns combined with verbs indicating action

    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
    478
    +0.21
    0.7%
    658
    +0.15
    0.5%
    1376
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.21
    0.12
    478
    +0.15
    0.09
    862
    +0.12
    0.06
    Negative Logits
    <bos>
    -0.62
     arată
    -0.60
     offerts
    -0.56
     ͜ʖ
    -0.52
     transfé
    -0.52
     jemanden
    -0.49
     écout
    -0.49
    BorderLayout
    -0.48
     devront
    -0.48
     الوطنيه
    -0.48
    POSITIVE LOGITS
     alre
    0.89
     guarante
    0.85
     intersper
    0.83
     inappro
    0.79
     emphat
    0.77
     depic
    0.76
     reluct
    0.75
     disreg
    0.74
     encomp
    0.74
     desir
    0.74
    Activations Density 0.476%

    No Known Activations