© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15175
    Prev
    Next
    INDEX
    Explanations

    references to scientific and technical terminology related to carbon and energy dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.61
    Tikang
    -0.61
    InvalidProtocol
    -0.60
    WithIdentifier
    -0.60
     losing
    -0.57
    фициальный
    -0.56
    IntoConstraints
    -0.56
    SharedDtor
    -0.54
     podjela
    -0.53
    CppMethod
    -0.53
    POSITIVE LOGITS
    tics
    0.69
    ksikon
    0.61
    ={()
    0.58
    newInstance
    0.56
     '\\;'
    0.56
    mysqli
    0.55
     Aw
    0.54
     Anne
    0.54
    bolista
    0.50
    vir
    0.49
    Activations Density 2.142%

    No Known Activations