© 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. 19-GEMMASCOPE-RES-16K
    11. 665
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological hierarchies and trends in food chains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppModule
    -0.59
    ItemBackground
    -0.55
    styleType
    -0.50
    jsonPath
    -0.45
     ioutil
    -0.44
     Dionys
    -0.43
    Климат
    -0.43
    outState
    -0.42
    SECTION
    -0.42
    urtstag
    -0.41
    POSITIVE LOGITS
     spectrum
    1.36
     scale
    1.35
     hierarchy
    1.22
     Scale
    1.13
     ladder
    1.11
     escala
    1.09
    spectrum
    1.06
    scale
    1.05
     continuum
    1.04
     scales
    1.03
    Activations Density 0.250%

    No Known Activations