Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5689
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to coding and programming constructs

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

    Preceding ordinal numbers or capitalized words

    np_acts-logits-general · gemini-2.0-flash

    adjective describing a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ientôt
    -0.51
     jagung
    -0.48
     Sachen
    -0.45
     perfeita
    -0.44
     Vereine
    -0.44
     Autorin
    -0.42
     Ärz
    -0.41
     Verhältnisse
    -0.41
     czę
    -0.41
     raça
    -0.40
    POSITIVE LOGITS
     MatDialog
    0.61
    Ārējās
    0.61
    abetes
    0.55
     ſch
    0.54
     ſche
    0.54
     Maf
    0.52
     ThemeData
    0.52
     дописавши
    0.51
     betweenstory
    0.51
     للمعارف
    0.49
    Activations Density 1.937%

    No Known Activations