© 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. 18-GEMMASCOPE-RES-16K
    11. 1759
    Prev
    Next
    INDEX
    Explanations

    connections between concepts or items in a comparative or exemplary context

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

    preceding exceptions ("but", "except")

    np_acts-logits-general · gemini-2.0-flash

    but

    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
    UnitTesting
    -0.57
     Segundo
    -0.46
    zenberg
    -0.44
    Segundo
    -0.42
    لیس
    -0.42
    kelen
    -0.42
    Regardless
    -0.41
     Xunit
    -0.41
     onCreate
    -0.41
    存于互联网档案馆
    -0.41
    POSITIVE LOGITS
    只不过
    1.32
     except
    1.25
     Except
    1.20
    Except
    1.11
    except
    1.11
     minus
    1.11
    minus
    1.08
     EXCEPT
    0.93
     albeit
    0.93
    不过是
    0.90
    Activations Density 0.492%

    No Known Activations