© 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. 28-GEMMASCOPE-RES-16K
    6. 4655
    Prev
    Next
    INDEX
    Explanations

    names of regions and nationalities

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

    Location or origin of something

    np_acts-logits-general · gemini-2.0-flash

    places ending in ia, x, or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.43
    تقاوى
    -0.40
    verwijspagina
    -0.36
    +#+#
    -0.35
    ///</
    -0.31
     disponibilités
    -0.31
    цездатний
    -0.31
    rungsseite
    -0.31
    يميديا
    -0.29
    landır
    -0.29
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.61
    󠁿
    0.59
    Florida
    0.57
     informée
    0.55
    Amer
    0.54
     Virginie
    0.54
    Melbourne
    0.54
    York
    0.54
    Carolina
    0.54
    ifornia
    0.53
    Activations Density 0.809%

    No Known Activations