Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13490
    Prev
    Next
    INDEX
    Explanations

    tokens representing numerical values and special symbols

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

    Tokens after currency symbols or numbers

    np_acts-logits-general · gemini-2.0-flash

    currency codes and mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.89
    хьтан
    -0.89
     AssemblyCulture
    -0.88
    DockStyle
    -0.87
    StructEnd
    -0.85
    rungsseite
    -0.84
     kasarigan
    -0.82
    StoryboardSegue
    -0.79
    tagHelperRunner
    -0.77
     estekak
    -0.75
    POSITIVE LOGITS
    >{@
    0.32
    ])))
    0.28
     siff
    0.28
    :
    0.26
    min
    0.25
    max
    0.25
     plong
    0.24
    __))
    0.24
     there
    0.24
    ])).
    0.23
    Activations Density 0.401%

    No Known Activations