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. 91928
    Prev
    Next
    INDEX
    Explanations

    parentheses and the structure of method declarations in code

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

    user turn indicator

    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
     def
    -0.34
    .
    -0.33
     de
    -0.31
    )
    -0.31
    -
    -0.30
     DEF
    -0.30
     lamp
    -0.30
     distance
    -0.29
     sentiment
    -0.29
     to
    -0.29
    POSITIVE LOGITS
     onCreate
    1.35
     ویکی‌پدی
    1.26
    MemoryWarning
    1.20
     onCreateView
    1.16
     AssemblyCulture
    1.13
     NSCoder
    1.13
     EconPapers
    1.12
    setVerticalGroup
    1.12
     يتيمه
    1.06
     viewDidLoad
    1.05
    Activations Density 0.000%

    No Known Activations