© 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. 17-GEMMASCOPE-RES-16K
    6. 4875
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes used for frontend navigation and modal dialogs

    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
     ga
    -0.44
    sp
    -0.43
    byes
    -0.43
     ap
    -0.42
     C
    -0.42
    OLIC
    -0.42
     sp
    -0.40
     AP
    -0.40
     аппетита
    -0.40
    仗
    -0.40
    POSITIVE LOGITS
     doubtnut
    0.79
    GenerationType
    0.79
     InputDecoration
    0.75
    OGND
    0.74
     $_"
    0.72
     IEnumerator
    0.72
     Audiodateien
    0.71
    windowFixed
    0.69
     photolibrary
    0.67
    Tembelea
    0.67
    Activations Density 0.038%

    No Known Activations