© 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. 18-GEMMASCOPE-RES-16K
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and conditions affecting justice

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

    scientific or medical concepts

    np_acts-logits-general · gemini-2.0-flash

    center of disk or planet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Colour
    -1.17
     fertil
    -1.16
     şi
    -1.13
    coloured
    -1.13
     generalised
    -1.11
     centralised
    -1.10
     utilisation
    -1.08
    Ещё
    -1.07
     unauthorised
    -1.05
     organisational
    -1.05
    POSITIVE LOGITS
     theaters
    1.37
     Ее
    1.35
     flavors
    1.31
     fibers
    1.29
     offenses
    1.26
     catalogs
    1.25
     molds
    1.24
     theater
    1.22
     Travelers
    1.21
     parlor
    1.19
    Activations Density 0.611%

    No Known Activations