© 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. 25-GEMMASCOPE-RES-16K
    11. 738
    Prev
    Next
    INDEX
    Explanations

    the presence of the specific term "Ro" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.62
     ['./
    -0.58
     insuffisamment
    -0.57
    TableAdapter
    -0.56
    aspectj
    -0.53
    IBOutlet
    -0.52
     ویکی‌پدیای
    -0.52
     Cedex
    -0.50
    帖最后由
    -0.49
    ImageContext
    -0.49
    POSITIVE LOGITS
    entgen
    0.56
    tisserie
    0.49
    ">:
    0.48
    Atsauces
    0.48
     FormControl
    0.47
    coco
    0.45
     resourceCulture
    0.45
     Chwiliwch
    0.45
    chester
    0.44
     ràng
    0.44
    Activations Density 0.215%

    No Known Activations