© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    mentioned names of people and locations in political discussions

    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
    1150
    +0.11
    0.3%
    344
    +0.10
    0.3%
    604
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.11
    0.04
    1136
    +0.10
    0.05
    1355
    +0.10
    0.04
    Negative Logits
     apprehen
    -0.73
     unwarran
    -0.72
     embodi
    -0.68
     encomp
    -0.68
     disagre
    -0.67
     tricot
    -0.66
     hairc
    -0.66
     liberality
    -0.65
     tolerably
    -0.64
     Ename
    -0.64
    POSITIVE LOGITS
     interviewer
    0.57
     interview
    0.55
     microphones
    0.54
     Paglinawan
    0.54
     intervi
    0.54
    ushchev
    0.52
     microphone
    0.50
     interviewing
    0.48
     reporters
    0.48
    enderror
    0.48
    Activations Density 0.626%

    No Known Activations