© 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. 2703
    Prev
    Next
    INDEX
    Explanations

    phrases involving personal understanding or acknowledgment of a situation

    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
    chyma
    -0.68
     contextLoads
    -0.67
     Wikimédia
    -0.67
    latego
    -0.61
     Vikipedi
    -0.59
     aastal
    -0.59
     wireType
    -0.59
     indirizzo
    -0.59
    @[+][
    -0.58
     Pliocene
    -0.57
    POSITIVE LOGITS
    According
    0.57
     ACCORD
    0.57
    Según
    0.57
     Menurut
    0.56
     According
    0.55
    according
    0.53
    Menurut
    0.52
     according
    0.51
    Selon
    0.51
     menurut
    0.51
    Activations Density 0.233%

    No Known Activations