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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5204
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person perspective in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.83
    CloseOperation
    -0.82
    RegressionTest
    -0.78
     jScrollPane
    -0.72
    లాలు
    -0.63
    enumi
    -0.63
    حياته
    -0.63
    يكب
    -0.63
    .');
    -0.61
    }');
    -0.61
    POSITIVE LOGITS
    writeField
    0.51
     dúvida
    0.47
    зулта
    0.45
     betweenstory
    0.45
    maal
    0.44
    ുറ
    0.43
    GetMapping
    0.42
    Gpio
    0.42
    λοι
    0.42
     [],
    0.41
    Activations Density 0.301%

    No Known Activations