© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2917
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.33
    1.6%
    241
    +0.13
    0.6%
    1334
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.33
    0.03
    1758
    +0.13
    0.03
    1334
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.91
     intersper
    -0.81
    /**
    -0.77
    ⓧ
    -0.67
    /***
    -0.67
     endeavoured
    -0.66
     disbur
    -0.63
    <?
    -0.61
     endow
    -0.61
     strove
    -0.60
    POSITIVE LOGITS
     affez
    0.80
     lapto
    0.76
     sembrano
    0.75
     Jambi
    0.73
     granat
    0.72
     tomat
    0.71
     keram
    0.71
    ubakar
    0.71
     Kemen
    0.70
     utop
    0.70
    Activations Density 0.055%

    No Known Activations