© 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. 5924
    Prev
    Next
    INDEX
    Explanations

    segments related to code structure and documentation

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

    Tokens after newline characters

    np_acts-logits-general · gemini-2.0-flash

    legal citations and currency codes

    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
     către
    -0.34
     calcetines
    -0.32
    ukseen
    -0.31
     mümkün
    -0.31
    operazione
    -0.30
     Apabila
    -0.30
    liesslich
    -0.30
     Verbraucher
    -0.30
     hareket
    -0.29
     guapos
    -0.29
    POSITIVE LOGITS
    IsMutable
    0.84
    !*\
    0.83
     kasarigan
    0.77
     незавершена
    0.75
    存于互联网档案馆
    0.74
    EndContext
    0.73
    ConstraintMaker
    0.72
     utafitiHapana
    0.72
    WriteLiteral
    0.72
    awtextra
    0.72
    Activations Density 0.175%

    No Known Activations