© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    terms related to web technologies and online services

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

    the internet, especially "Web"

    np_acts-logits-general · gemini-2.0-flash

    web services and browsing

    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
    ValueStyle
    -0.56
    !*\
    -0.54
    Rptr
    -0.52
    BufferException
    -0.47
     autorytatywna
    -0.46
    __":
    
    -0.46
     Italijanski
    -0.46
    YourGuide
    -0.45
    styleType
    -0.44
     SwitchCompat
    -0.44
    POSITIVE LOGITS
     Web
    0.63
     web
    0.61
     WEB
    0.58
    Web
    0.56
     Webber
    0.55
    webs
    0.54
    web
    0.53
     webs
    0.52
     Webster
    0.49
    WEB
    0.46
    Activations Density 0.092%

    No Known Activations