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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6195
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "can be" and variations of "to be" in different contexts

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

    "Can be" followed by a past participle

    np_acts-logits-general · gemini-2.0-flash

    can be followed by verb

    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
    ölle
    -0.40
    hogy
    -0.39
    principalColumn
    -0.39
    setto
    -0.38
     nakalista
    -0.38
    ọa
    -0.38
    printStats
    -0.37
    ImageIO
    -0.37
    Ord
    -0.36
     toal
    -0.36
    POSITIVE LOGITS
    CanBe
    0.69
     can
    0.64
     تضيفلها
    0.61
    Podemos
    0.57
    Puedes
    0.56
     bulunabilir
    0.55
     gärna
    0.54
     puteți
    0.53
     ניתן
    0.52
     lze
    0.52
    Activations Density 0.247%

    No Known Activations