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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 1051
    Prev
    Next
    INDEX
    Explanations

    references to the pop singer Katy Perry and her associated appearances or mentions

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

    names and surnames

    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
    scriptcase
    -0.47
     Aloha
    -0.42
    substring
    -0.42
    rungsseite
    -0.39
    Elias
    -0.39
     CIRC
    -0.38
     Mgr
    -0.38
     Trix
    -0.38
     jTextField
    -0.38
     AppCompatTheme
    -0.37
    POSITIVE LOGITS
    Hentet
    0.63
    qvarna
    0.62
    letoe
    0.61
     Winaray
    0.56
    IntoConstraints
    0.52
    期刊论文
    0.50
     Witherspoon
    0.48
    IndentedString
    0.48
     invokingState
    0.46
    bangun
    0.45
    Activations Density 0.007%

    No Known Activations