© 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. 831
    Prev
    Next
    INDEX
    Explanations

    characters and symbols related to references or categorization

    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
    bootstrapcdn
    -0.48
    ActionTypes
    -0.48
     gynnwys
    -0.48
    PYX
    -0.47
    WriteTagHelper
    -0.45
     Nimbus
    -0.45
    ization
    -0.44
     onCreateView
    -0.44
    AccessFile
    -0.44
     PyTuple
    -0.43
    POSITIVE LOGITS
     lenker
    0.59
    FunctionFlags
    0.58
     sumpay
    0.56
    :✨
    0.52
    CloseOperation
    0.51
     kasarigan
    0.50
    THISDAY
    0.47
     Dulles
    0.47
    eli
    0.46
    Dtor
    0.46
    Activations Density 0.175%

    No Known Activations