© 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. 7179
    Prev
    Next
    INDEX
    Explanations

    specific skills or characteristics associated with various astrological signs and mythical creatures

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

    Constellation names

    np_acts-logits-general · gemini-2.0-flash

    constellation names

    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
    AddTagHelper
    -0.62
    ulgação
    -0.45
    Ligações
    -0.44
    BagLayout
    -0.40
    лтемелер
    -0.40
    protoimpl
    -0.39
     Produktions
    -0.39
     Paglinawan
    -0.39
    ilever
    -0.39
    geleitet
    -0.39
    POSITIVE LOGITS
     constellations
    0.52
     constellation
    0.52
    ябре
    0.45
     pue
    0.44
    ugges
    0.42
     stars
    0.41
    Dlg
    0.40
    دانشنامهٔ
    0.40
    Wass
    0.40
     Zeich
    0.40
    Activations Density 0.219%

    No Known Activations