© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3962
    Prev
    Next
    INDEX
    Explanations

    references to latitude and its variation in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.55
     nahilalakip
    -0.44
     snippetHide
    -0.43
    {{\
    -0.42
     piper
    -0.40
    httphttps
    -0.40
     localVar
    -0.38
     pert
    -0.37
    OOTDTY
    -0.37
     Kuala
    -0.36
    POSITIVE LOGITS
     lat
    0.76
    Lat
    0.69
     Lat
    0.65
    lat
    0.64
    ut
    0.59
    Encoding
    0.55
     Encoding
    0.55
     Expo
    0.55
    LAT
    0.53
    Ges
    0.53
    Activations Density 0.616%

    No Known Activations