© 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. 23-GEMMASCOPE-RES-16K
    6. 9060
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems and responsibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.67
    yntaxException
    -0.66
    OGND
    -0.66
    UserScript
    -0.56
     вікі
    -0.55
    Personendaten
    -0.54
    InjectAttribute
    -0.54
    SharedCtor
    -0.54
    SpringRunner
    -0.52
    postIndex
    -0.52
    POSITIVE LOGITS
     vastaan
    0.41
     demnach
    0.38
     cuivre
    0.38
    釁
    0.37
     följande
    0.36
     enthalten
    0.36
     aprove
    0.36
     faveur
    0.36
    PRWEB
    0.35
     marbre
    0.35
    Activations Density 0.911%

    No Known Activations