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. 108784
    Prev
    Next
    INDEX
    Explanations

    mentions of orchestras and orchestral groups

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

    the followed by proper nouns

    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
    AddTagHelper
    -0.77
     autorytatywna
    -0.74
    webElement
    -0.72
     doInBackground
    -0.57
    lover
    -0.55
    BASELINE
    -0.54
    ChildScrollView
    -0.54
     okuyayım
    -0.54
    XmlAccessType
    -0.54
     Waterfall
    -0.54
    POSITIVE LOGITS
     subsequently
    0.40
    sequently
    0.37
     Subsequently
    0.36
    yarnpkg
    0.33
     NUKAT
    0.33
    Източници
    0.33
     later
    0.32
    像
    0.31
    +/**
    0.31
     što
    0.31
    Activations Density 0.072%

    No Known Activations