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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6276
    Prev
    Next
    INDEX
    Explanations

    key phrases related to policy proposals, legislation, and analysis

    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
    1643
    +0.09
    0.3%
    581
    +0.09
    0.2%
    849
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.09
    0.05
    914
    +0.09
    0.02
    1650
    +0.08
    0.04
    Negative Logits
     „,
    -0.73
     maroc
    -0.73
     Ueb
    -0.69
     Schrö
    -0.67
     stoff
    -0.67
     bayern
    -0.67
     Hül
    -0.67
     ciment
    -0.66
     Kün
    -0.65
     Frö
    -0.65
    POSITIVE LOGITS
     hardest
    0.92
     fastest
    0.89
     heaviest
    0.84
     brightest
    0.84
     highest
    0.83
     strongest
    0.82
     lowest
    0.82
     longest
    0.81
     quickest
    0.81
    highest
    0.81
    Activations Density 0.516%

    No Known Activations