© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8481
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to visual and spatial details of scenes

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

    Animation or cartoon-related contexts

    np_acts-logits-general · gemini-2.0-flash

    Baileywick gives Sofia swans

    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
    IntoConstraints
    -0.47
     noDo
    -0.47
     suicidio
    -0.47
    SharedDtor
    -0.45
     négo
    -0.45
    enterOuterAlt
    -0.43
     raped
    -0.43
    RectangleBorder
    -0.42
     onBind
    -0.42
    migrationBuilder
    -0.42
    POSITIVE LOGITS
     cartoon
    0.70
     anthrop
    0.69
     adventures
    0.60
     animation
    0.59
     wacky
    0.58
     mischievous
    0.57
     adventure
    0.57
     animated
    0.55
     cartoons
    0.54
     inventions
    0.52
    Activations Density 0.622%

    No Known Activations