© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 96379
    Prev
    Next
    INDEX
    Explanations

    references to various types of media and entertainment, particularly related to nostalgia and childhood experiences

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

    LEGO sets and Technic models

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Filmografie
    -0.57
    ismet
    -0.54
    apimachinery
    -0.50
     estekak
    -0.48
    textAppearance
    -0.47
    bukkit
    -0.46
    hyrchwyd
    -0.45
    FXML
    -0.45
     comp
    -0.43
    DrawerToggle
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.45
    AndEndTag
    0.45
    Personendaten
    0.39
    ValueStyle
    0.39
    LEGO
    0.37
     LEGO
    0.36
     peças
    0.35
     SEÑ
    0.35
    ignoire
    0.34
    zijn
    0.34
    Activations Density 0.042%

    No Known Activations