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. 6868
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "nation" or "national identity."

    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
    +0.26
    1.6%
    204
    +0.12
    0.7%
    1937
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.26
    0.03
    1926
    +0.12
    0.03
    67
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.95
     reimburse
    -0.60
     absorb
    -0.57
     grab
    -0.56
    芹
    -0.56
    جغرافيا
    -0.55
    cover
    -0.55
     accompany
    -0.55
     synthesize
    -0.54
     supervise
    -0.54
    POSITIVE LOGITS
     sergio
    1.36
     affor
    1.35
     leonardo
    1.33
     milf
    1.33
     madonna
    1.30
     wikihow
    1.30
     unlaw
    1.29
     Abbé
    1.28
     ecru
    1.27
     chrysler
    1.27
    Activations Density 0.040%

    No Known Activations