© 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. 14784
    Prev
    Next
    INDEX
    Explanations

    mentions of the benefits and attractiveness of playing video games

    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
    198
    +0.13
    0.4%
    1265
    +0.10
    0.3%
    581
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.13
    0.06
    908
    +0.10
    0.03
    1243
    +0.10
    0.05
    Negative Logits
     rispond
    -0.62
     catég
    -0.51
    anyone
    -0.50
     setti
    -0.50
    registrer
    -0.50
    Népesség
    -0.50
     Alat
    -0.49
     Passe
    -0.49
    Anything
    -0.49
    Anyone
    -0.49
    POSITIVE LOGITS
    SneakyThrows
    0.79
     unwarran
    0.77
     shewn
    0.76
     BIBSYS
    0.71
     liberality
    0.69
     whofe
    0.68
     jopa
    0.65
     ftre
    0.65
     pymongo
    0.63
     laft
    0.62
    Activations Density 0.464%

    No Known Activations