© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8081
    Prev
    Next
    INDEX
    Explanations

    specific wildlife species mentioned in the document

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

    animals

    np_acts-logits-general · gemini-2.0-flash

    animals and birds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.68
    ViewImports
    -0.68
    IsContent
    -0.67
     صوتيه
    -0.66
    adaptiveStyles
    -0.63
    enumi
    -0.61
     NgModule
    -0.57
    ModelState
    -0.56
     Púb
    -0.55
    enumii
    -0.55
    POSITIVE LOGITS
     deer
    0.66
     humming
    0.64
     birds
    0.64
     migrating
    0.63
     <<<<<<<<<<<<<<
    0.62
     geese
    0.61
     turtles
    0.61
     racco
    0.60
     bears
    0.59
     cardinals
    0.58
    Activations Density 0.367%

    No Known Activations