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. 31-GEMMASCOPE-RES-16K
    6. 16288
    Prev
    Next
    INDEX
    Explanations

    code related to Android Fragment lifecycle methods and their components

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

    Java fragments and related code

    np_acts-logits-general · gemini-2.0-flash

    fragment instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    runOnUiThread
    -0.60
     AssemblyTitle
    -0.58
     getApplication
    -0.40
     getIntent
    -0.40
    readAs
    -0.39
     iNdEx
    -0.38
     applicants
    -0.37
    Ivoire
    -0.37
     plaintiffs
    -0.36
     happiest
    -0.36
    POSITIVE LOGITS
     onCreateView
    0.75
     Fragment
    0.65
    Fragment
    0.63
     fragment
    0.63
    fragment
    0.61
    onViewCreated
    0.60
    GOTREF
    0.51
     frag
    0.50
    setStyle
    0.48
    newInstance
    0.48
    Activations Density 0.049%

    No Known Activations