© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3671
    Prev
    Next
    INDEX
    Explanations

    mentions of the NFL

    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
    1438
    +0.12
    0.4%
    1741
    +0.10
    0.3%
    1363
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.12
    0.03
    1178
    +0.10
    0.04
    1141
    +0.10
    0.03
    Negative Logits
    oa̍t
    -0.60
     xxvi
    -0.57
     xxiii
    -0.57
     répondit
    -0.55
     zima
    -0.55
    itosan
    -0.54
     xxiv
    -0.52
     xxii
    -0.52
     xxv
    -0.51
     zis
    -0.51
    POSITIVE LOGITS
    NFL
    0.97
     NFL
    0.89
     Trasp
    0.64
    NHL
    0.62
     NHL
    0.61
     nfl
    0.60
    <bos>
    0.59
     Boulogne
    0.58
    NBA
    0.57
    Lma
    0.57
    Activations Density 0.089%

    No Known Activations