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
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7229
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various tenses and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.79
     Geſch
    -0.62
    Datuak
    -0.62
     Roskov
    -0.58
    mejores
    -0.57
     pungkas
    -0.57
    tagHelperRunner
    -0.55
     Waſſer
    -0.55
    eventually
    -0.54
    DeleteBehavior
    -0.54
    POSITIVE LOGITS
    正在
    0.49
     đang
    0.49
    gridLayout
    0.45
     
    0.44
    errHandler
    0.41
    I
    0.39
    >//
    0.38
     trying
    0.38
     piv
    0.38
     engag
    0.38
    Activations Density 0.486%

    No Known Activations