© 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. 20-GEMMASCOPE-RES-16K
    11. 5232
    Prev
    Next
    INDEX
    Explanations

    elements related to literature and fiction, particularly focusing on books and stories

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

    literary/publishing terms related to books and writing, such as 'novella', 'novelette', and 'stories'.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    Dead
    -0.45
    Public
    -0.39
    isAlive
    -0.39
    Indian
    -0.37
    isDead
    -0.37
    ...”
    -0.37
     Zoro
    -0.37
    StandardCharsets
    -0.37
     Dead
    -0.36
     Public
    -0.36
    POSITIVE LOGITS
    parsedMessage
    0.86
     AssemblyCompany
    0.70
     typelib
    0.68
    verwijspagina
    0.61
     HasFactory
    0.60
    ANDUM
    0.60
    tanleria
    0.60
     Roskov
    0.59
     للاسماء
    0.58
    DrawerToggle
    0.58
    Activations Density 0.603%

    No Known Activations