© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1822
    Prev
    Next
    INDEX
    Explanations

    references to areas or regions referred to as "zones"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.69
    ioca
    -0.58
     asti
    -0.57
    __*/
    -0.56
    りと
    -0.55
    arov
    -0.53
     McGuire
    -0.52
    gyz
    -0.51
     procede
    -0.51
     Pará
    -0.50
    POSITIVE LOGITS
     zone
    3.60
     Zone
    3.47
     zones
    3.22
     ZONE
    3.17
    zone
    3.16
    Zone
    3.15
     Zones
    3.11
    zones
    2.76
    ZONE
    2.74
    Zones
    2.66
    Activations Density 0.027%

    No Known Activations