© 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. 10920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direct actions or effects

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

    "direct" or "directly"

    np_acts-logits-general · gemini-2.0-flash

    direct or unmediated

    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
    ChildScrollView
    -0.44
    harapkan
    -0.41
    ENDIAN
    -0.39
     bumpers
    -0.39
    WriteTagHelper
    -0.39
    AnimationsModule
    -0.39
     løpet
    -0.38
     sauve
    -0.38
    orianCalendar
    -0.37
    avelength
    -0.37
    POSITIVE LOGITS
     direct
    2.19
    Direct
    2.14
    direct
    2.13
     directly
    1.96
     Direct
    1.92
    directly
    1.88
     Directly
    1.80
     DIRECT
    1.78
     directe
    1.78
    直接
    1.77
    Activations Density 0.181%

    No Known Activations