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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7235
    Prev
    Next
    INDEX
    Explanations

    references to specific routes, possibly in the context of sports, travel, or programming

    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
    553
    +0.15
    0.6%
    1581
    +0.14
    0.6%
    1983
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.15
    0.02
    1983
    +0.14
    0.02
    1581
    +0.14
    0.02
    Negative Logits
     Février
    -0.78
     Septembre
    -0.76
     Travail
    -0.75
     velours
    -0.73
     Prés
    -0.71
     Sén
    -0.69
     Juillet
    -0.69
     carrefour
    -0.67
     porcelaine
    -0.67
     Lég
    -0.66
    POSITIVE LOGITS
     route
    1.48
     Route
    1.38
    route
    1.34
     routes
    1.33
    Route
    1.26
     ROUTE
    1.19
    ROUTE
    1.13
     Routes
    1.13
    routes
    1.10
    Routes
    1.03
    Activations Density 0.069%

    No Known Activations