Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10921
    Prev
    Next
    INDEX
    Explanations

    elements and attributes from programming or markup languages, particularly related to data handling and response mechanisms

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

    Code snippets or programming-related content

    np_acts-logits-general · gemini-2.0-flash

    PHP JSON parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.57
     typelib
    -0.54
     CreateTagHelper
    -0.54
    });*/
    -0.53
    krivning
    -0.52
     فريبيس
    -0.51
    };*/
    -0.50
    ])))
    -0.49
     ModelExpression
    -0.49
     Jefus
    -0.49
    POSITIVE LOGITS
     Савезне
    0.43
     muur
    0.40
     afspraak
    0.38
    /******/
    0.37
    SupportActionBar
    0.36
     EnglishChoose
    0.36
     skala
    0.35
    GEBURTS
    0.35
     kaarangay
    0.35
    scale
    0.34
    Activations Density 0.304%

    No Known Activations