Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12543
    Prev
    Next
    INDEX
    Explanations

    technical terms related to semiconductor devices and their electrical properties

    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
    LookAnd
    -0.68
    StoryboardSegue
    -0.60
    FieldDescriptor
    -0.56
    FieldNumber
    -0.54
     estekak
    -0.54
    richTextPanel
    -0.53
     springfox
    -0.53
    SafeMath
    -0.53
    giène
    -0.53
     onPostExecute
    -0.53
    POSITIVE LOGITS
     Package
    0.72
     package
    0.71
    Package
    0.69
     PACKAGE
    0.65
     packaged
    0.63
     packages
    0.61
    package
    0.60
     RoHS
    0.59
     виправивши
    0.58
     packaging
    0.58
    Activations Density 0.394%

    No Known Activations