© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7679
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically the Netherlands

    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
    200
    +0.14
    0.5%
    314
    +0.10
    0.3%
    971
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.14
    0.02
    227
    +0.10
    0.04
    629
    +0.10
    0.02
    Negative Logits
    Daar
    -0.78
    woor
    -0.75
    Waar
    -0.73
     Daar
    -0.71
     Waar
    -0.70
    reportWebVitals
    -0.66
     Wiking
    -0.66
    Welke
    -0.65
    Samen
    -0.62
    ssohn
    -0.61
    POSITIVE LOGITS
     dutch
    1.33
     McLaugh
    1.26
     Dutch
    1.20
     Dutchman
    1.16
    dutch
    1.15
     impra
    1.15
     wherea
    1.15
     reluct
    1.14
     McInt
    1.12
     Leurs
    1.12
    Activations Density 0.169%

    No Known Activations