© 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. 11288
    Prev
    Next
    INDEX
    Explanations

    verbs in the gerund form, specifically those that come after the preposition "to"

    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
    +0.14
    0.4%
    545
    +0.11
    0.3%
    390
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.14
    0.05
    1415
    +0.11
    0.04
    545
    +0.10
    0.05
    Negative Logits
     „,
    -1.02
     fta
    -0.96
    iented
    -0.94
     thut
    -0.93
    esterday
    -0.92
     fup
    -0.89
     grati
    -0.89
     fré
    -0.88
    uvres
    -0.88
     aen
    -0.87
    POSITIVE LOGITS
     consider
    0.73
     avoid
    0.69
     дописавши
    0.69
     keep
    0.69
    <bos>
    0.68
     explore
    0.67
     conosce
    0.67
     pursue
    0.66
     achieve
    0.65
     devemos
    0.65
    Activations Density 0.190%

    No Known Activations