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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1132
    Prev
    Next
    INDEX
    Explanations

    information related to sports injuries and player status

    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
    906
    +0.09
    0.3%
    344
    +0.09
    0.3%
    736
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1312
    +0.09
    0.05
    736
    +0.09
    0.05
    1330
    +0.07
    0.03
    Negative Logits
     embodi
    -1.11
     pollut
    -1.08
     roberto
    -0.99
     ricardo
    -0.99
     unwarran
    -0.96
     sergio
    -0.95
     alberto
    -0.94
     zirc
    -0.94
     suscep
    -0.94
     impractica
    -0.94
    POSITIVE LOGITS
     kompati
    0.61
     injured
    0.59
    Presentación
    0.59
     minimalis
    0.57
     injury
    0.56
     kosme
    0.55
     due
    0.55
     peruan
    0.53
     induk
    0.53
    Зноскі
    0.52
    Activations Density 0.327%

    No Known Activations