© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7104
    Prev
    Next
    INDEX
    Explanations

    information related to video games, including titles, features, and development details

    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
    690
    +0.13
    0.4%
    304
    +0.13
    0.4%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2007
    +0.13
    0.04
    678
    +0.13
    0.06
    441
    +0.09
    0.05
    Negative Logits
    XMLSchema
    -0.65
    Vaata
    -0.63
     fince
    -0.61
     eorum
    -0.58
     whofe
    -0.57
     feen
    -0.56
     المعيارى
    -0.56
     sarili
    -0.55
     oxalate
    -0.54
    HtmlAttribute
    -0.52
    POSITIVE LOGITS
     broderie
    0.85
     tricot
    0.84
     bandeau
    0.83
     spé
    0.74
     cushi
    0.74
     velour
    0.73
     snapback
    0.70
     Pièces
    0.69
     hairc
    0.69
     tén
    0.69
    Activations Density 0.667%

    No Known Activations