© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7671
    Prev
    Next
    INDEX
    Explanations

    icon-related elements 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 @ 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
    StructEnd
    -1.04
    /***/
    -1.02
    NameInMap
    -0.99
    UnusedPrivate
    -0.97
     ་་
    -0.96
    ::::::::::::::::
    -0.94
    \{\\
    -0.93
     يتيمه
    -0.93
    Hozzáférés
    -0.92
     Houſe
    -0.92
    POSITIVE LOGITS
     icon
    2.32
    icon
    2.27
     Icon
    2.26
    Icon
    2.05
     icons
    1.99
    ICON
    1.93
     ICON
    1.85
     Icons
    1.82
    Icons
    1.76
    icons
    1.74
    Activations Density 0.027%

    No Known Activations