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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6871
    Prev
    Next
    INDEX
    Explanations

    terms related to layout specifications in programming contexts

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

    Refers to the bottom or padding-bottom CSS property

    np_acts-logits-general · gemini-2.0-flash

    directions and spacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.49
     onCreateView
    -0.47
    ỡng
    -0.46
    futbolista
    -0.45
    AnimationsModule
    -0.44
    complexType
    -0.44
    Microkernel
    -0.44
    IndentedString
    -0.44
     InputDecoration
    -0.43
    haikusbot
    -0.40
    POSITIVE LOGITS
    borderBottom
    0.63
    paddingBottom
    0.57
    bottom
    0.57
    Bottom
    0.55
    paddingTop
    0.54
    borderTop
    0.54
    paddingVertical
    0.53
     bottom
    0.52
     marginBottom
    0.51
    paddingRight
    0.50
    Activations Density 0.255%

    No Known Activations