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. 5-GEMMASCOPE-RES-16K
    6. 3478
    Prev
    Next
    INDEX
    Explanations

    references to time periods and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ):=\
    -0.56
    CloseOperation
    -0.55
    }$)
    -0.53
    าสตร์
    -0.49
     initComponents
    -0.49
     فا
    -0.48
    principalColumn
    -0.47
    ientí
    -0.47
    }:=\
    -0.46
    ]").
    -0.46
    POSITIVE LOGITS
    FieldBuilder
    0.92
     esternos
    0.80
    Демографія
    0.78
     câte
    0.75
    protoimpl
    0.73
     ویکی‌پدی
    0.70
     apiece
    0.67
     Picchu
    0.64
     HttpNotFound
    0.63
    المكان
    0.63
    Activations Density 0.105%

    No Known Activations