© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7703
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and software development

    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
    StructEnd
    -0.55
    __((
    -0.48
    InstrumentedTest
    -0.44
    jsonwebtoken
    -0.44
     predict
    -0.44
     heran
    -0.43
     HttpNotFound
    -0.43
    Engineers
    -0.43
    Thunk
    -0.43
     investors
    -0.43
    POSITIVE LOGITS
     Roskov
    0.62
    xsi
    0.58
     xmlns
    0.57
     xlink
    0.55
     Narrative
    0.51
     SHALL
    0.51
    Narrative
    0.51
     coded
    0.50
     Qualifier
    0.50
     Occurrence
    0.50
    Activations Density 1.030%

    No Known Activations