© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7869
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and scientific components

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

    Followed by position, group, or solution

    np_acts-logits-general · gemini-2.0-flash

    position and group identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Areas
    -0.59
    Classes
    -0.58
    Series
    -0.57
    Functionality
    -0.57
     Categories
    -0.57
    Structures
    -0.57
     سكانية
    -0.57
    Produkt
    -0.56
    Seasons
    -0.56
    Categories
    -0.55
    POSITIVE LOGITS
     purpoſe
    0.65
     medel
    0.65
    assertRaises
    0.65
    دانشنامهٔ
    0.63
     perſon
    0.56
     resourceCulture
    0.56
     ragion
    0.56
     Enviar
    0.56
    <bos>
    0.55
    Hentet
    0.55
    Activations Density 1.124%

    No Known Activations