© 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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6791
    Prev
    Next
    INDEX
    Explanations

    key geographic locations and contextual references related to regions or areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.53
     Numerade
    -0.49
    contentLoaded
    -0.48
    BeginContext
    -0.48
     noDo
    -0.46
     Krakowie
    -0.44
     <>",
    -0.44
    ronpa
    -0.44
    reportWebVitals
    -0.43
    IndentedString
    -0.42
    POSITIVE LOGITS
     district
    1.58
     District
    1.36
    district
    1.28
     DISTRICT
    1.22
    District
    1.21
     districts
    1.18
    DISTRICT
    1.10
     Districts
    1.02
     distrito
    0.98
     dist
    0.96
    Activations Density 0.292%

    No Known Activations