© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10955
    Prev
    Next
    INDEX
    Explanations

    references to app-related components and libraries in programming code

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

    Code snippets or imports

    np_acts-logits-general · gemini-2.0-flash

    technical terms and abbreviations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    LookAnd
    -0.45
    omock
    -0.44
    ValueStyle
    -0.40
    COLLE
    -0.38
    scrapy
    -0.38
    RUnlock
    -0.36
    Viitteet
    -0.35
    tagHelperRunner
    -0.35
    orianCalendar
    -0.35
     bere
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.59
     betweenstory
    0.50
    iexcl
    0.49
    HomeAsUpEnabled
    0.47
    BufferException
    0.47
     незавершена
    0.47
     Bewußt
    0.45
    Jahr
    0.45
    ayuno
    0.44
     pozw
    0.44
    Activations Density 0.481%

    No Known Activations