© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    titles of films, books, and articles

    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
    297
    +0.13
    0.4%
    776
    +0.12
    0.4%
    906
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.13
    0.06
    147
    +0.12
    0.03
    575
    +0.12
    0.04
    Negative Logits
     xxiii
    -0.56
     xxv
    -0.56
    Bedankt
    -0.56
    Veel
    -0.56
     xxvi
    -0.55
    Jakie
    -0.55
     regardant
    -0.54
    Prí
    -0.53
    Pře
    -0.53
     whofe
    -0.53
    POSITIVE LOGITS
     minimalis
    0.82
     palab
    0.77
     utop
    0.73
     gmbh
    0.72
     demen
    0.71
     kuns
    0.70
     abnorm
    0.70
     lapto
    0.70
     verba
    0.69
     pietre
    0.69
    Activations Density 0.318%

    No Known Activations