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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 14956
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents or emergencies involving visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    different kinds of light sources

    np_acts-logits-general · gemini-2.0-flash

    technical processes and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stolic
    -0.49
    ContextHolder
    -0.44
    कारी
    -0.43
    BASEPATH
    -0.42
    Pfalz
    -0.41
     متعلقه
    -0.41
    ViewFeatures
    -0.41
    fromnode
    -0.40
    dsl
    -0.39
    Erstellt
    -0.38
    POSITIVE LOGITS
    MemoryWarning
    0.75
    RectangleBorder
    0.68
    onActivityResult
    0.61
    ResumeLayout
    0.60
    DeleteBehavior
    0.59
    migrationBuilder
    0.58
    contentLoaded
    0.56
     Ahead
    0.56
     ſmall
    0.55
    Ahead
    0.55
    Activations Density 0.503%

    No Known Activations