© 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. 20-GEMMASCOPE-RES-16K
    11. 7905
    Prev
    Next
    INDEX
    Explanations

    sentence endings and punctuation marks

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

    Follows a period in technical or formal writing

    np_acts-logits-general · gemini-2.0-flash

    objective or purpose

    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
     ModelExpression
    -0.73
    `,
    -0.72
     FetchType
    -0.71
    ChildScrollView
    -0.71
     MotionEvent
    -0.69
    󠁮
    -0.66
    Hozzáférés
    -0.65
    `;
    -0.64
    ällor
    -0.64
    enumii
    -0.64
    POSITIVE LOGITS
    Objective
    0.93
     PURPOSE
    0.93
    Abstract
    0.92
     Objective
    0.91
    Purpose
    0.90
     OBJECTIVE
    0.88
     Abstract
    0.83
    ABSTRACT
    0.83
    OBJECTIVE
    0.83
     objective
    0.81
    Activations Density 0.909%

    No Known Activations