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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8617
    Prev
    Next
    INDEX
    Explanations

    keywords related to films that are based on novels or real events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    rungsseite
    -0.58
    InputBorder
    -0.58
    providedIn
    -0.55
    FieldBuilder
    -0.51
    Jegyzetek
    -0.47
     BorderSide
    -0.47
    AnimationsModule
    -0.43
     profesión
    -0.42
    posedge
    -0.41
     kolik
    -0.41
    POSITIVE LOGITS
     мәкалә
    0.40
    Espèce
    0.38
     concept
    0.37
    idea
    0.37
     story
    0.36
     ide
    0.36
    概念
    0.36
     kese
    0.36
    inspired
    0.36
    acamata
    0.35
    Activations Density 0.136%

    No Known Activations