© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1431
    Prev
    Next
    INDEX
    Explanations

    phrases related to references in media, particularly pertaining to specific films or characters

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

    Text before parentheses, periods, or x

    np_acts-logits-general · gemini-2.0-flash

    voiced, how do, to find, was lost

    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
     GenerationType
    -0.48
     fisuras
    -0.46
    ✨:
    -0.43
    لينكات
    -0.43
     rospy
    -0.42
     diciendo
    -0.41
     Lleva
    -0.40
     almendras
    -0.40
    entibus
    -0.40
     colazione
    -0.39
    POSITIVE LOGITS
    yarnpkg
    0.50
    Clik
    0.45
    참고
    0.43
     EconPapers
    0.42
    +:+
    0.42
    PostInfinity
    0.42
    ResumeLayout
    0.41
    Nuorodos
    0.41
    老
    0.39
    UnknownFieldSet
    0.39
    Activations Density 0.389%

    No Known Activations