© 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. 18-GEMMASCOPE-RES-16K
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    references to specific pieces of advice or recommendations related to problem-solving

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

    file paths or code

    np_acts-logits-general · gemini-2.0-flash

    страницы, блоки, предложения, ошибки, praci

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.71
     kasarigan
    -0.66
    berdayakan
    -0.64
    estrian
    -0.62
    ficial
    -0.61
    photobucket
    -0.61
     Wikiseite
    -0.60
    теризу
    -0.60
     huh
    -0.59
     shy
    -0.58
    POSITIVE LOGITS
    ReusableCell
    0.81
     typelib
    0.50
    MessageTagHelper
    0.48
    Kariera
    0.48
     Survive
    0.45
    encodeWith
    0.44
    Джерела
    0.43
    RenderAtEndOf
    0.43
    organisation
    0.42
     становника
    0.40
    Activations Density 0.059%

    No Known Activations