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. 16062
    Prev
    Next
    INDEX
    Explanations

    references related to geographical locations and statistics

    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
    +0.14
    0.4%
    1177
    +0.11
    0.3%
    1042
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.14
    0.05
    1726
    +0.11
    0.02
    870
    +0.07
    0.04
    Negative Logits
    €/
    -0.77
     €/
    -0.76
    ;;)
    -0.74
     abnorm
    -0.73
     utop
    -0.70
     recipro
    -0.70
     ?...
    -0.70
     galo
    -0.70
     incess
    -0.69
     dises
    -0.68
    POSITIVE LOGITS
     currently
    0.73
     Currently
    0.65
     presently
    0.62
    Currently
    0.58
     Presently
    0.57
    currently
    0.56
     worldwide
    0.52
     total
    0.52
     nationwide
    0.52
     current
    0.50
    Activations Density 0.414%

    No Known Activations