© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5941
    Prev
    Next
    INDEX
    Explanations

    references to turtles and crocodiles

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

    turtles or crocodiles

    np_acts-logits-general · gemini-2.0-flash

    reptiles like crocodiles and turtles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.51
     gamis
    -0.48
    #+#
    -0.47
    mergeFrom
    -0.47
    ✨:
    -0.45
    wpi
    -0.45
     vst
    -0.45
     Bilbao
    -0.45
    setArguments
    -0.44
    تفصیلات
    -0.43
    POSITIVE LOGITS
     turtle
    1.37
     Turtle
    1.21
     turtles
    1.19
    Turtle
    1.10
     tortoise
    1.09
    turtle
    1.08
     Turtles
    1.00
     Tortoise
    0.94
    🐢
    0.89
     torto
    0.88
    Activations Density 0.222%

    No Known Activations