© 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. 18-GEMMASCOPE-RES-16K
    6. 4831
    Prev
    Next
    INDEX
    Explanations

    mentions of lakes and related bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Appears after "Lake"

    np_acts-logits-general · gemini-2.0-flash

    lake names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.71
    ScopeManager
    -0.67
    CloseOperation
    -0.63
    ContextHolder
    -0.54
    KommentareTeilen
    -0.53
    Hij
    -0.51
    geant
    -0.51
    Convenience
    -0.49
     Diretto
    -0.49
    зни
    -0.49
    POSITIVE LOGITS
     lakes
    1.05
    Lakes
    0.94
     lake
    0.93
     Lakes
    0.93
    lakes
    0.92
     Lake
    0.88
    Lake
    0.81
     LAKE
    0.77
    lake
    0.75
    LAKE
    0.75
    Activations Density 0.089%

    No Known Activations