Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15915
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions, particularly those associated with the term "West."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "West" or its variants

    np_acts-logits-general · gemini-2.0-flash

    West with geographical region

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.80
    JNIEnv
    -0.78
     
    -0.70
    úly
    -0.70
     NgModule
    -0.68
    دانشنامهٔ
    -0.67
    Paraguay
    -0.67
     Numerade
    -0.66
    MetaObject
    -0.65
    stealth
    -0.64
    POSITIVE LOGITS
     Westwood
    0.84
     occidentale
    0.83
     WEST
    0.83
    West
    0.83
     Weston
    0.80
    Wes
    0.76
    esse
    0.75
     Wes
    0.73
     Westen
    0.72
     West
    0.72
    Activations Density 0.108%

    No Known Activations