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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1713
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or specific locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    227
    +0.12
    0.3%
    1013
    +0.08
    0.2%
    1862
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    284
    +0.08
    0.06
    1013
    +0.07
    0.06
    Negative Logits
     reger
    -0.71
     logis
    -0.67
     erit
    -0.62
     tenden
    -0.61
     ordina
    -0.60
     gesta
    -0.59
     tages
    -0.58
     vola
    -0.57
     tuc
    -0.57
     hek
    -0.57
    POSITIVE LOGITS
     shortly
    0.67
    posób
    0.66
     pymongo
    0.63
     pymysql
    0.60
     early
    0.59
     last
    0.59
     Shortly
    0.59
     late
    0.58
     earlier
    0.57
     בשנת
    0.57
    Activations Density 0.472%

    No Known Activations