© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7598
    Prev
    Next
    INDEX
    Explanations

    specific references to statistical analysis and mathematical frameworks in academic papers

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

    Text within brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    academic paper endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.62
    MigrationBuilder
    -0.53
     चीज़ों
    -0.51
    tagext
    -0.51
    ismet
    -0.50
    fortawesome
    -0.49
    تقاوى
    -0.49
    клопе
    -0.47
    WithIOException
    -0.47
    Hentet
    -0.44
    POSITIVE LOGITS
     The
    0.59
     quæ
    0.47
     How
    0.47
    }],
    
    0.46
     Anwendung
    0.45
    The
    0.45
     Grecs
    0.44
    How
    0.44
     själva
    0.41
    Global
    0.40
    Activations Density 0.298%

    No Known Activations