© 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. 17-GEMMASCOPE-RES-16K
    6. 12158
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keyColumn
    -0.62
    onViewCreated
    -0.61
    RegistryLite
    -0.59
    UserScript
    -0.55
     nghiệp
    -0.53
     calendriers
    -0.53
    buster
    -0.52
     Pera
    -0.52
     yyl
    -0.52
    GeneratedCode
    -0.51
    POSITIVE LOGITS
     //$
    0.56
     MainAxisSize
    0.54
    зулта
    0.54
    %"),
    0.53
     Roskov
    0.53
    :][
    0.53
    --)
    
    0.53
     تانيه
    0.50
    ANTLR
    0.49
     lips
    0.47
    Activations Density 0.013%

    No Known Activations