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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 521
    Prev
    Next
    INDEX
    Explanations

    sentences that present additional information or context

    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
    +0.29
    1.2%
    2019
    +0.10
    0.4%
    381
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1950
    +0.29
    0.04
    2019
    +0.10
    0.05
    63
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.82
    /***
    -0.68
    //---
    -0.68
    //*/
    -0.56
    //----
    -0.56
    thâu
    -0.52
    ⓧ
    -0.52
    ///**
    -0.52
     inaugurate
    -0.52
     restre
    -0.51
    POSITIVE LOGITS
     devenus
    0.80
     épu
    0.79
     lele
    0.78
     expérimentés
    0.77
     saka
    0.77
     récents
    0.76
     animés
    0.76
    />";
    0.75
    siyah
    0.74
     />";
    0.74
    Activations Density 0.370%

    No Known Activations