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. 15-GEMMASCOPE-RES-16K
    6. 5092
    Prev
    Next
    INDEX
    Explanations

    elements and terminology related to healthcare, particularly in context with service provision

    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
    1
    -0.57
    .
    -0.56
    8
    -0.53
     moeite
    -0.53
    9
    -0.51
    3
    -0.51
    7
    -0.50
    is
    -0.50
     adicionais
    -0.49
     with
    -0.48
    POSITIVE LOGITS
     doInBackground
    0.99
     ComVisible
    0.96
    ChildScrollView
    0.86
     дописавши
    0.86
    MigrationBuilder
    0.84
     AttributeSet
    0.84
    ^(@
    0.83
     ostavi
    0.82
    HasAnnotation
    0.82
     Мексичка
    0.82
    Activations Density 0.208%

    No Known Activations