© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    terms related to the measurement and attributes of sizes and dimensions

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

    the word "size"

    np_acts-logits-general · gemini-2.0-flash

    size and its assignment

    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
     Gouver
    -0.45
    >{@
    -0.40
     gorra
    -0.40
     "..\..\
    -0.38
     Gamb
    -0.38
     Pra
    -0.38
    げて
    -0.37
     palanca
    -0.37
    NSUserDefaults
    -0.37
    Accademia
    -0.37
    POSITIVE LOGITS
     Size
    1.47
    Size
    1.42
     SIZE
    1.35
     size
    1.34
    size
    1.34
    SIZE
    1.32
     getSize
    1.18
     Sizes
    1.15
    getSize
    1.10
     sizes
    1.09
    Activations Density 0.178%

    No Known Activations