Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    patterns of movement or transitions in 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
    +0.25
    0.9%
    1535
    +0.11
    0.4%
    1742
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.25
    0.02
    1094
    +0.11
    0.03
    1962
    +0.10
    0.02
    Negative Logits
    <bos>
    -1.98
    Organisateur
    -0.59
    Referències
    -0.52
    phi
    -0.52
    dress
    -0.51
    sav
    -0.50
    Более
    -0.50
    put
    -0.49
    FailureListener
    -0.49
    ounid
    -0.49
    POSITIVE LOGITS
     dott
    0.94
    ;;)
    0.91
     signora
    0.91
     pymysql
    0.90
     Lycée
    0.90
    postolic
    0.89
     bambina
    0.88
    stasia
    0.88
     Czechos
    0.88
     paradiso
    0.87
    Activations Density 0.206%

    No Known Activations