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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5155
    Prev
    Next
    INDEX
    Explanations

    terms associated with mathematical equations or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valid
    -0.49
    ódz
    -0.49
    árbol
    -0.48
     légitime
    -0.48
    주의
    -0.47
    +#+
    -0.45
     Leeuwen
    -0.43
    葩
    -0.42
    assertNull
    -0.42
    kuwa
    -0.41
    POSITIVE LOGITS
    ChildScrollView
    0.80
    Espèce
    0.74
    ponses
    0.68
    TargetException
    0.66
    JspWriter
    0.65
     <=",
    0.64
    RefreshLayout
    0.63
    IMPORTED
    0.61
    styleType
    0.61
    FormTagHelper
    0.60
    Activations Density 1.251%

    No Known Activations