© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms and statistics

    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
    599
    +0.17
    0.5%
    764
    +0.13
    0.4%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.12
    599
    +0.13
    0.09
    1870
    +0.12
    0.05
    Negative Logits
    parsedMessage
    -0.63
    Apesar
    -0.59
    Fußball
    -0.55
    собенности
    -0.54
    Preço
    -0.52
    Manbalar
    -0.52
     kasarigan
    -0.51
    Ainda
    -0.50
    حوالہ
    -0.49
    <bos>
    -0.49
    POSITIVE LOGITS
     reluct
    1.42
     accla
    1.39
     shenan
    1.36
     increa
    1.35
     affor
    1.31
     madonna
    1.29
     peppa
    1.29
     indestru
    1.28
     depic
    1.27
     excru
    1.27
    Activations Density 1.152%

    No Known Activations