© 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. 16-GEMMASCOPE-RES-16K
    11. 8829
    Prev
    Next
    INDEX
    Explanations

    elements related to annotations in programming code

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

    "annotation"

    np_acts-logits-general · gemini-2.0-flash

    annotation or judicial nominees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.88
    Према
    -0.77
     unknownFields
    -0.76
    Portail
    -0.73
    +#+#
    -0.72
    انجليز
    -0.71
    SourceChecksum
    -0.69
    LinkId
    -0.69
     eorum
    -0.67
    ChildScrollView
    -0.65
    POSITIVE LOGITS
    annotation
    1.83
    annotations
    1.16
    Annotation
    1.15
     annotation
    1.13
     Annotation
    1.10
    Annotations
    1.08
    DataAnnotations
    1.07
    注解
    0.84
     annotations
    0.83
    躇
    0.79
    Activations Density 0.035%

    No Known Activations