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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14816
    Prev
    Next
    INDEX
    Explanations

    specific references to historical events, especially related to governance and social issues

    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
    776
    +0.15
    0.4%
    1013
    +0.14
    0.4%
    1967
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.15
    0.03
    776
    +0.14
    0.03
    1008
    +0.11
    0.02
    Negative Logits
    !!</
    -0.92
     „,
    -0.92
     pixabay
    -0.91
     lele
    -0.90
     idr
    -0.85
     vnd
    -0.84
     thut
    -0.82
     ?</
    -0.80
     »>
    -0.79
     autunno
    -0.78
    POSITIVE LOGITS
     century
    0.81
    th
    0.64
    century
    0.63
    entieth
    0.60
     Century
    0.56
    Jeez
    0.55
     decade
    0.54
    Thief
    0.53
     period
    0.51
    Bruh
    0.51
    Activations Density 0.042%

    No Known Activations