© 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. 7523
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe ease or efficiency in actions

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

    Adverbs describing ease or manner

    np_acts-logits-general · gemini-2.0-flash

    ease and effectiveness

    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
    новништво
    -0.74
     ujednoznacz
    -0.71
     Roskov
    -0.67
    principalColumn
    -0.64
    DrawerToggle
    -0.64
    endpush
    -0.61
     linkovi
    -0.60
    AddTagHelper
    -0.58
    Geplaatst
    -0.58
    UserScript
    -0.57
    POSITIVE LOGITS
     parlant
    0.38
    నే
    0.34
     by
    0.34
     once
    0.32
     asisten
    0.31
    mente
    0.31
    ‌تر
    0.31
     enough
    0.30
     as
    0.30
     Sn
    0.29
    Activations Density 0.487%

    No Known Activations