© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific context

    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
    581
    +0.13
    0.4%
    1978
    +0.12
    0.4%
    674
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1747
    +0.13
    0.04
    499
    +0.12
    0.04
    776
    +0.12
    0.04
    Negative Logits
    Literat
    -0.62
     ghz
    -0.61
    Continuar
    -0.58
    Fordítás
    -0.58
     Ottobre
    -0.58
     Giugno
    -0.57
    muito
    -0.57
     scuro
    -0.56
    ñora
    -0.56
    Herzlich
    -0.56
    POSITIVE LOGITS
    <bos>
    0.73
     tolerably
    0.65
     disagre
    0.62
     endeavored
    0.60
     quitted
    0.58
     NUKAT
    0.58
     impelled
    0.58
     reconno
    0.57
     vainly
    0.56
     unwarran
    0.55
    Activations Density 0.166%

    No Known Activations