© 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. 9079
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of seating or locations associated with a "bench."

    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
    routeProvider
    -0.66
    HasAnnotation
    -0.65
     <<<<<<<<<<<<<<
    -0.62
     nonatomic
    -0.58
     thị
    -0.56
    queryInterface
    -0.56
    цездатний
    -0.55
    synthesize
    -0.53
    >{@
    -0.53
    #+#
    -0.52
    POSITIVE LOGITS
     bench
    1.13
    bench
    0.89
     Bench
    0.89
     benches
    0.89
    Bench
    0.81
    Level
    0.74
     Level
    0.71
    level
    0.68
     leveling
    0.68
     levelling
    0.65
    Activations Density 0.116%

    No Known Activations