© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    GPS-related terms and location-based information

    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
    313
    +0.13
    0.5%
    201
    +0.12
    0.4%
    871
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.13
    0.02
    678
    +0.12
    0.02
    201
    +0.12
    0.01
    Negative Logits
     Varan
    -0.55
     Kig
    -0.51
     Madura
    -0.51
    ResponseWriter
    -0.48
     abond
    -0.46
    Билгалдахарш
    -0.46
    idać
    -0.45
    MessageOf
    -0.45
    geslacht
    -0.45
     Rè
    -0.44
    POSITIVE LOGITS
     geo
    1.02
     GPS
    0.98
     Geo
    0.89
     geographic
    0.88
    GPS
    0.86
     GEO
    0.83
     geography
    0.83
    Geo
    0.82
     Geographic
    0.81
     geographical
    0.81
    Activations Density 0.083%

    No Known Activations