© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4581
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to aquatic activities and marine life

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

    Water and sea related terms

    np_acts-logits-general · gemini-2.0-flash

    marine and water environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.69
    RectangleBorder
    -0.67
     disambiguazione
    -0.66
    tagHelperRunner
    -0.62
    ----</
    -0.61
    principalColumn
    -0.61
     OnInit
    -0.59
    DotNetBar
    -0.59
     kasarigan
    -0.58
    IntoConstraints
    -0.57
    POSITIVE LOGITS
    side
    0.39
     Ground
    0.39
    DrawerLayout
    0.38
    FileChooser
    0.36
     ground
    0.35
    way
    0.34
    ground
    0.33
    lawn
    0.32
    ken
    0.31
    len
    0.31
    Activations Density 0.330%

    No Known Activations