© 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
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6339
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and family interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.45
     linkovi
    -0.44
    PerformLayout
    -0.43
     endregion
    -0.43
     sockaddr
    -0.43
    TypedDataSet
    -0.42
    fjspx
    -0.42
    ラク
    -0.41
    KommentareTeilen
    -0.40
    contentLoaded
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.44
     fell
    0.44
     jatuh
    0.40
     afspraak
    0.40
     lingered
    0.39
    keur
    0.39
     took
    0.39
     stumbled
    0.38
     испыта
    0.38
    AsUp
    0.37
    Activations Density 0.124%

    No Known Activations