© 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. 25-GEMMASCOPE-RES-16K
    6. 9008
    Prev
    Next
    INDEX
    Explanations

    references to programming classes, functions, and their interactions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     قد
    -0.39
    itemid
    -0.38
     Must
    -0.37
     must
    -0.37
     pipa
    -0.36
     bird
    -0.36
     Vern
    -0.36
     Shall
    -0.35
     Jewel
    -0.35
     Ord
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.96
     createState
    0.84
    хьтан
    0.81
    contentLoaded
    0.80
    DotNetBar
    0.75
    LLocation
    0.75
     intptr
    0.71
    tagHelperRunner
    0.71
    SharedDtor
    0.71
    KURZBESCHREIBUNG
    0.70
    Activations Density 0.315%

    No Known Activations