© 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. 3364
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events or government-related activities and procedures

    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
    1616
    +0.10
    0.3%
    1437
    +0.09
    0.3%
    1778
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.10
    0.07
    1616
    +0.09
    0.06
    194
    +0.09
    0.03
    Negative Logits
     currently
    -0.57
     Currently
    -0.55
    currentPosition
    -0.55
    Current
    -0.55
    current
    -0.54
    currently
    -0.52
     Current
    -0.52
     now
    -0.51
     Presently
    -0.49
    now
    -0.49
    POSITIVE LOGITS
     originally
    0.66
     originalmente
    0.62
    Katso
    0.60
     interesan
    0.59
    ⓧ
    0.57
     wasnt
    0.57
    FTFY
    0.56
    wasn
    0.56
     acompaña
    0.56
    ējās
    0.55
    Activations Density 0.926%

    No Known Activations