© 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. 20-GEMMASCOPE-RES-16K
    6. 14243
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure attributes and manipulations

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

    Refers to sizes or lengths

    np_acts-logits-general · gemini-2.0-flash

    size and length measurements

    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
     OFDb
    -0.51
    Transkript
    -0.46
    "),
    
    -0.45
     {},
    
    -0.44
     Wiktionnaire
    -0.43
    %"),
    -0.42
    openConnection
    -0.41
     ")";
    -0.41
     ExecuteAsync
    -0.41
    OGND
    -0.40
    POSITIVE LOGITS
     Hauteur
    0.47
    JsonHelper
    0.43
    totalSupply
    0.42
    autogui
    0.42
     Tenga
    0.42
     Kopf
    0.42
    clerView
    0.42
     Verdad
    0.42
    QMetaType
    0.41
    Lire
    0.41
    Activations Density 0.608%

    No Known Activations