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. 7-GEMMASCOPE-RES-16K
    6. 15151
    Prev
    Next
    INDEX
    Explanations

    components related to text input fields in user interface elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withIdentifier
    -0.89
    TypedDataSet
    -0.79
    +#+#
    -0.73
    Geplaatst
    -0.66
     ?>/
    -0.66
    raszamy
    -0.65
     imageNamed
    -0.65
    VersionUID
    -0.64
    DispatchToProps
    -0.63
    BeginContext
    -0.63
    POSITIVE LOGITS
    JTextField
    1.14
    TextBox
    1.04
    textarea
    1.00
    EditText
    0.98
     TextField
    0.95
    TextField
    0.93
    textField
    0.90
     TextEditing
    0.88
     JTextField
    0.87
     UITextField
    0.87
    Activations Density 0.063%

    No Known Activations