© 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. 24-GEMMASCOPE-RES-16K
    6. 5855
    Prev
    Next
    INDEX
    Explanations

    references to legal entities and their related activities

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

    Proper noun followed by a business-related word

    np_acts-logits-general · gemini-2.0-flash

    names and entities in investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gedrag
    -0.39
     enamorado
    -0.36
     perilaku
    -0.32
     acogedor
    -0.32
     deportivo
    -0.32
     transportasi
    -0.31
     gesunde
    -0.30
     vectorielle
    -0.30
     paesi
    -0.30
     kohta
    -0.30
    POSITIVE LOGITS
     '{@
    0.59
     Pythag
    0.57
    TRIBUN
    0.56
     referenties
    0.56
     prot
    0.56
    uxxxx
    0.55
     Caucus
    0.55
     ProtoMessage
    0.55
     Chromat
    0.54
    ſchaft
    0.54
    Activations Density 0.805%

    No Known Activations