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. 1227
    Prev
    Next
    INDEX
    Explanations

    terms related to diseases and medical conditions

    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
    +0.14
    0.5%
    1443
    +0.11
    0.4%
    61
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1443
    +0.14
    0.04
    147
    +0.11
    0.03
    509
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.56
    Collections
    -0.80
     arrange
    -0.80
    順
    -0.77
     consider
    -0.76
    주
    -0.73
    述
    -0.72
     stand
    -0.71
    stand
    -0.71
    <eos>
    -0.71
    POSITIVE LOGITS
     swarovski
    2.54
     ecru
    2.30
     stockholm
    2.20
     Mlle
    2.04
     bandung
    2.03
     hairc
    2.01
     broderie
    2.01
     Abbé
    1.99
     sergio
    1.97
     aquarelle
    1.95
    Activations Density 0.408%

    No Known Activations