© 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. 20-GEMMASCOPE-RES-16K
    11. 367
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of taking or removing

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

    Something being taken away

    np_acts-logits-general · gemini-2.0-flash

    taking away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.70
    Havolalar
    -0.63
    LookAnd
    -0.58
     purpoſe
    -0.58
    andoah
    -0.58
    interopRequire
    -0.56
    IonicModule
    -0.55
    onViewCreated
    -0.54
     Jefus
    -0.54
    省市镇
    -0.54
    POSITIVE LOGITS
     away
    1.60
     Away
    1.26
     snatched
    1.23
     AWAY
    1.20
    away
    1.19
    Away
    1.18
     stolen
    1.04
     snatch
    1.02
    AWAY
    1.02
     taken
    0.98
    Activations Density 0.211%

    No Known Activations