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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 34583
    Prev
    Next
    INDEX
    Explanations

    sections labeled as "abstract" or similar variations indicating the presence of summaries

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

    abstract, affirm

    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
    MLLoader
    -0.68
    AnimationsModule
    -0.57
    medriver
    -0.56
    ulemon
    -0.56
    serviceWorker
    -0.50
    xhttp
    -0.50
     GoogleFonts
    -0.49
    InputBorder
    -0.49
     تعدى
    -0.49
     WebDriverWait
    -0.49
    POSITIVE LOGITS
    abstract
    2.92
     abstract
    2.05
    Abstract
    1.84
     Abstract
    1.71
     ABSTRACT
    1.63
    ABSTRACT
    1.57
     abstracts
    1.52
     abstracta
    1.43
     abstra
    1.41
     abstrait
    1.38
    Activations Density 0.000%

    No Known Activations