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. 764
    Prev
    Next
    INDEX
    Explanations

    phrases related to division, collaboration, and the dynamics of social interactions

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

    Adjectives that describe something

    np_acts-logits-general · gemini-2.0-flash

    qualities describing nouns

    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
    évaluateur
    -0.46
    Tembelea
    -0.45
    الدراسه
    -0.43
    ImageContext
    -0.42
    tinyos
    -0.42
    OPSIS
    -0.41
     
    -0.40
     Khart
    -0.40
     Normandy
    -0.40
    ⌉
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.56
    transQ
    0.48
     الحره
    0.44
    EDEFAULT
    0.44
    adaptiveStyles
    0.42
    gebnisse
    0.40
     conoscenza
    0.40
    eseorang
    0.40
     autorytatywna
    0.39
     Relaciones
    0.38
    Activations Density 0.758%

    No Known Activations