© 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. 28-GEMMASCOPE-RES-16K
    6. 4483
    Prev
    Next
    INDEX
    Explanations

    discussions about collective experiences and group interactions

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

    Text that follows a period or URL

    np_acts-logits-general · gemini-2.0-flash

    podcast or listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neón
    -0.42
     åt
    -0.38
    rativa
    -0.36
     Venedig
    -0.36
     wydaj
    -0.32
     Verfasser
    -0.31
     vidéos
    -0.31
    layoutControl
    -0.31
    テレビ
    -0.29
     melihat
    -0.29
    POSITIVE LOGITS
     listeners
    1.42
     podcast
    1.38
     listener
    1.33
    Podcast
    1.23
     Podcast
    1.21
     podcasts
    1.19
    podcast
    1.16
     Listen
    1.12
     Listener
    1.11
     listen
    1.09
    Activations Density 0.191%

    No Known Activations