Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15453
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries or political events

    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
    50
    +0.31
    1.2%
    1741
    +0.23
    0.9%
    2019
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.31
    0.07
    16
    +0.23
    0.09
    1435
    +0.19
    0.06
    Negative Logits
     rayures
    -0.77
     vété
    -0.77
     gardien
    -0.77
     noël
    -0.74
     soeur
    -0.74
     trouva
    -0.73
     oeil
    -0.73
     monstre
    -0.72
    ypeł
    -0.72
     vérit
    -0.72
    POSITIVE LOGITS
     entire
    0.70
     majority
    0.65
     biggest
    0.60
     whole
    0.57
     reason
    0.56
    Katso
    0.56
     current
    0.54
     largest
    0.53
     greatest
    0.53
     chances
    0.52
    Activations Density 0.373%

    No Known Activations