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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9771
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal terminology and processes

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

    Follows a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    legal or formal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.58
    TagMode
    -0.56
    styleType
    -0.54
    StructEnd
    -0.48
    الحياه
    -0.45
    titleMargin
    -0.44
    ⓧ
    -0.42
    TargetException
    -0.40
    TagHelper
    -0.40
    ficulties
    -0.40
    POSITIVE LOGITS
    ſelves
    0.46
    
    0.45
     fubject
    0.45
    LookAnd
    0.44
    .*")]
    0.42
     CallOverrides
    0.42
     Houſe
    0.40
    wiſe
    0.40
     ComVisible
    0.38
     Aufen
    0.38
    Activations Density 2.722%

    No Known Activations