© 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. 895
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures

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

    Code related to "class" or "namespace"

    np_acts-logits-general · gemini-2.0-flash

    class definitions

    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
    Personendaten
    -0.68
    BindView
    -0.63
     CreateTagHelper
    -0.61
    تقاوى
    -0.61
     JADX
    -0.60
    MigrationBuilder
    -0.60
    GOTREF
    -0.59
    AndEndTag
    -0.56
    ➟
    -0.55
     Sainsbury
    -0.54
    POSITIVE LOGITS
     виправивши
    0.62
     class
    0.56
    class
    0.51
     gehö
    0.51
    setClass
    0.50
    export
    0.49
     gehör
    0.49
     experts
    0.47
    Newswire
    0.47
     export
    0.46
    Activations Density 0.015%

    No Known Activations