© 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. 15-GEMMASCOPE-RES-16K
    11. 1957
    Prev
    Next
    INDEX
    Explanations

    Java class definitions and their attributes, including extensions and implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.52
     
    -0.50
     con
    -0.44
     no
    -0.41
     sp
    -0.41
    ...
    -0.41
    足
    -0.40
     by
    -0.40
    ch
    -0.39
     ParseException
    -0.39
    POSITIVE LOGITS
    ^(@)
    1.03
     getBase
    1.03
     Efq
    0.95
    tvguidetime
    0.93
    tagHelperRunner
    0.90
    Abstract
    0.90
    BaseController
    0.90
     itſelf
    0.90
    вгений
    0.88
     $_"
    0.87
    Activations Density 0.214%

    No Known Activations