© 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. 7270
    Prev
    Next
    INDEX
    Explanations

    copyright information and references in texts

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

    Copyright statements

    np_acts-logits-general · gemini-2.0-flash

    copyright notices

    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
     Houſe
    -0.53
    moiselle
    -0.53
    majánló
    -0.52
     nakalista
    -0.50
    seille
    -0.48
    Descripció
    -0.48
    ſchen
    -0.48
    iſen
    -0.47
    Chham
    -0.47
    RELAND
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.68
     ©️
    0.59
     ©
    0.53
    ©
    0.46
    
    0.42
    
    0.41
    TagMode
    0.40
    awtextra
    0.40
    GEBURTSDATUM
    0.39
     AssemblyProduct
    0.37
    Activations Density 0.135%

    No Known Activations