© 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. 1831
    Prev
    Next
    INDEX
    Explanations

    mentions of potential future events or developments

    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
    674
    +0.22
    0.7%
    1967
    +0.11
    0.4%
    630
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    898
    +0.22
    0.08
    1819
    +0.11
    0.12
    630
    +0.11
    0.08
    Negative Logits
    TagMode
    -1.05
     ***!
    -0.90
    IsContent
    -0.83
     Baillargeon
    -0.78
    archiviato
    -0.77
     للمعارف
    -0.75
    StandardCharsets
    -0.75
    adalajara
    -0.74
    BoxShadow
    -0.73
    الصفحه
    -0.72
    POSITIVE LOGITS
     intersper
    2.55
     encomp
    2.53
     increa
    2.50
     impra
    2.47
     affor
    2.46
     disagre
    2.45
     maneu
    2.42
     reluct
    2.40
     accla
    2.39
     shenan
    2.39
    Activations Density 1.656%

    No Known Activations