Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 82440
    Prev
    Next
    INDEX
    Explanations

    references to school and related concepts

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

    school-aged children and activities

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Nieren
    -0.42
     Gewebe
    -0.40
     Ursache
    -0.39
     Jedes
    -0.39
     remains
    -0.39
     scheme
    -0.38
     combination
    -0.38
    цепт
    -0.36
     diamants
    -0.36
    ungkin
    -0.35
    POSITIVE LOGITS
    Afternoon
    0.75
    afternoon
    0.74
     afternoon
    0.65
     Afternoon
    0.65
     afternoons
    0.64
    AddTagHelper
    0.60
    MLLoader
    0.56
    Lunch
    0.51
     CreateTagHelper
    0.51
     extracurricular
    0.50
    Activations Density 0.003%

    No Known Activations