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. 1530
    Prev
    Next
    INDEX
    Explanations

    political and societal references related to America's past and present and economic disparities

    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
    764
    +0.09
    0.3%
    1253
    +0.09
    0.2%
    1533
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    781
    +0.09
    0.04
    1181
    +0.09
    0.04
    1543
    +0.08
    0.04
    Negative Logits
     karna
    -0.57
     AspNetCore
    -0.56
    tagHelperRunner
    -0.54
     kasama
    -0.54
     kahit
    -0.53
    yari
    -0.52
    duled
    -0.52
    oredCriteria
    -0.50
     muna
    -0.50
     habang
    -0.50
    POSITIVE LOGITS
     bianche
    0.55
     Allegretto
    0.54
     Valentín
    0.53
     Abbiamo
    0.52
     Horacio
    0.48
     Siamo
    0.48
    Caratter
    0.47
     vecchi
    0.47
     rosse
    0.47
     trânsito
    0.46
    Activations Density 0.413%

    No Known Activations