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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9627
    Prev
    Next
    INDEX
    Explanations

    code-related declarations and access modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     שוליים
    -0.62
    ChildScrollView
    -0.61
    StoryboardSegue
    -0.53
    penser
    -0.50
    LayoutInflater
    -0.45
    dicionado
    -0.44
    OTTEN
    -0.42
    Kinds
    -0.41
    hots
    -0.40
    OSIS
    -0.40
    POSITIVE LOGITS
    دانشنامهٔ
    0.81
     يتيمه
    0.67
     AssemblyCompany
    0.64
    يكب
    0.60
     Efq
    0.58
    CGRectMake
    0.58
    +#+#
    0.56
    verwijspagina
    0.55
     CGRectMake
    0.54
    principalTable
    0.53
    Activations Density 0.065%

    No Known Activations