© 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. 8422
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and affirmations

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

    Code snippets with "Just" and a past tense verb

    np_acts-logits-general · gemini-2.0-flash

    just followed by verb or adjective

    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
     مرئيه
    -0.45
    ranslated
    -0.44
     varm
    -0.42
    ossed
    -0.41
    ritic
    -0.40
    MethodManager
    -0.38
    冲击
    -0.38
     congratulate
    -0.38
     geophysical
    -0.37
    内の
    -0.37
    POSITIVE LOGITS
     betweenstory
    0.56
    LookAnd
    0.52
    ItemBackground
    0.52
     AssemblyCompany
    0.50
    AsUp
    0.49
    ViewImports
    0.49
     informée
    0.49
     Wikiseite
    0.44
    WebpackPlugin
    0.43
    Nuorodos
    0.43
    Activations Density 0.504%

    No Known Activations