© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8797
    Prev
    Next
    INDEX
    Explanations

    references to default configurations and settings 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imageshack
    -0.60
     MessageBoxIcon
    -0.57
    ocities
    -0.50
     Autorisations
    -0.46
    quiry
    -0.46
     ChromeDriver
    -0.44
    BASEPATH
    -0.44
    MenuInflater
    -0.44
     Houſe
    -0.43
     AttributeSet
    -0.43
    POSITIVE LOGITS
     default
    1.23
    default
    1.19
     Default
    1.09
    DEFAULT
    1.00
    Default
    1.00
     DEFAULT
    0.98
     daily
    0.94
     defaults
    0.89
    daily
    0.82
     defaulted
    0.82
    Activations Density 0.177%

    No Known Activations