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. 9-GEMMASCOPE-RES-16K
    6. 15733
    Prev
    Next
    INDEX
    Explanations

    numerical data and terms related to mathematical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.69
     NSCoder
    -0.68
    ]</
    -0.67
    setVerticalGroup
    -0.67
    MLLoader
    -0.66
    ?]
    -0.65
    ]^{-
    -0.65
    }`)
    -0.64
     ་་
    -0.64
    ...]
    -0.64
    POSITIVE LOGITS
    Aktualisiert
    0.55
     olduk
    0.46
    InjectMocks
    0.45
     Italijani
    0.45
     dolayı
    0.45
     önem
    0.42
    Fig
    0.42
     vertes
    0.41
     blå
    0.41
    .
    0.41
    Activations Density 1.438%

    No Known Activations