© 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. 6196
    Prev
    Next
    INDEX
    Explanations

    words related to drilling and hydraulic fracturing (fracking)

    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
    31
    +0.19
    0.8%
    976
    +0.15
    0.6%
    629
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    629
    +0.19
    0.02
    31
    +0.15
    0.02
    976
    +0.14
    0.03
    Negative Logits
     كومونز
    -0.56
    MigrationBuilder
    -0.48
     Arn
    -0.46
     Bernice
    -0.42
     Lorna
    -0.42
    Arn
    -0.41
    nestjs
    -0.41
     Pence
    -0.41
    NewUrlParser
    -0.39
    Enlaces
    -0.39
    POSITIVE LOGITS
     Fra
    1.33
     fra
    1.25
    Fra
    1.18
    fra
    1.12
     FRAG
    0.99
     FRA
    0.97
     frag
    0.96
     Fract
    0.94
     fragment
    0.92
     fract
    0.91
    Activations Density 0.096%

    No Known Activations