© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10899
    Prev
    Next
    INDEX
    Explanations

    percentages related to product effectiveness and satisfaction

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

    "100%" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    100% followed by words

    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
    ándola
    -0.27
     ähnliche
    -0.27
     few
    -0.27
     pocos
    -0.26
    슷
    -0.26
     birkaç
    -0.26
     câteva
    -0.25
     ménage
    -0.25
     Trauer
    -0.25
     tatlı
    -0.25
    POSITIVE LOGITS
    Personendaten
    1.00
     AssemblyCompany
    0.94
    +#+#
    0.93
     المعيارى
    0.93
    évaluateur
    0.85
    ########.
    0.82
    cshtml
    0.81
    fjspx
    0.80
    GEBURTSDATUM
    0.79
    principalTable
    0.79
    Activations Density 0.191%

    No Known Activations