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. 2194
    Prev
    Next
    INDEX
    Explanations

    chemical processes and conditions related to reactions and temperature adjustments

    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
    SharedDtor
    -0.52
    tagHelperRunner
    -0.51
    nonatomic
    -0.51
    anci
    -0.46
     considérons
    -0.45
     المعيارى
    -0.44
    헌
    -0.43
    unnitel
    -0.42
     storico
    -0.42
     Carry
    -0.42
    POSITIVE LOGITS
    OGND
    0.65
    原始内容存档于
    0.62
    \}\\
    0.60
    RetentionPolicy
    0.59
    ientôt
    0.58
     simplicité
    0.58
    MemoryWarning
    0.58
     createState
    0.57
    CompleteListener
    0.53
    RectangleBorder
    0.52
    Activations Density 0.601%

    No Known Activations