© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10425
    Prev
    Next
    INDEX
    Explanations

    phrases indicating variability or dependence on different factors or conditions

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

    "depending on"

    np_acts-logits-general · gemini-2.0-flash

    depending on

    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
     successfully
    -0.35
     inwardly
    -0.30
     trenches
    -0.29
     present
    -0.28
     bitte
    -0.28
     free
    -0.28
     ע
    -0.28
     SPIRIT
    -0.27
     tự
    -0.27
     spirit
    -0.27
    POSITIVE LOGITS
    depending
    1.27
     depending
    1.26
    Depending
    1.19
     Depending
    1.15
     dependiendo
    1.07
     tergantung
    1.02
    Depends
    1.00
     Depends
    1.00
    depends
    0.99
     afhankelijk
    0.95
    Activations Density 0.480%

    No Known Activations