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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12742
    Prev
    Next
    INDEX
    Explanations

    code snippets and method declarations in programming files, particularly related to Objective-C and Swift syntax

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

    Objective-C method declarations/signatures

    np_acts-logits-general · gemini-2.0-flash

    Objective-C method signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Ỉ
    -0.46
     FontFamily
    -0.42
    خره
    -0.42
     Genu
    -0.41
    ticale
    -0.41
    orique
    -0.41
    Inde
    -0.39
     Weeks
    -0.39
    çim
    -0.39
     neighbor
    -0.39
    POSITIVE LOGITS
    WriteTagHelper
    0.98
    id
    0.65
    لیس
    0.64
    nullable
    0.63
    extAlignment
    0.61
     المعيارى
    0.61
    iastes
    0.60
     gynhyrchwyd
    0.60
    idopsis
    0.60
    httphttps
    0.59
    Activations Density 0.130%

    No Known Activations