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. 18-GEMMASCOPE-RES-16K
    6. 14638
    Prev
    Next
    INDEX
    Explanations

    Java-related GUI components and their manipulations

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

    Text input fields and related properties

    np_acts-logits-general · gemini-2.0-flash

    text input fields and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.89
    contentLoaded
    -0.69
    SequentialGroup
    -0.67
    withIdentifier
    -0.65
    Сылтамалар
    -0.62
    createServer
    -0.61
    ListItemIcon
    -0.61
     Meksiku
    -0.60
    StructEnd
    -0.60
    DrawerLayout
    -0.58
    POSITIVE LOGITS
     TextEditing
    0.75
    TextWatcher
    0.71
     Input
    0.66
     Validators
    0.65
     TextInput
    0.64
    TextEditing
    0.62
     placeholder
    0.61
     typing
    0.61
    Input
    0.61
     UITextField
    0.60
    Activations Density 0.115%

    No Known Activations