© 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. 15-GEMMASCOPE-RES-16K
    6. 4941
    Prev
    Next
    INDEX
    Explanations

    elements related to practical tasks and services, especially in the context of performing and creating

    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
     >=",
    -0.70
     թվական
    -0.58
    SharedCtor
    -0.57
    клопе
    -0.57
    rinus
    -0.55
    Superclass
    -0.55
     تانيه
    -0.53
    LookAnd
    -0.53
    errHandler
    -0.52
    WithMany
    -0.51
    POSITIVE LOGITS
     own
    1.42
     sendiri
    1.29
     zelf
    1.28
     Own
    1.25
     eigener
    1.17
    Own
    1.14
     selber
    1.11
     соб
    1.11
     egna
    1.10
     egen
    1.09
    Activations Density 0.306%

    No Known Activations