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. 8-GEMMASCOPE-RES-16K
    6. 6234
    Prev
    Next
    INDEX
    Explanations

    CSS positioning properties and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.75
    IsContent
    -0.58
     BoxFit
    -0.56
    Facades
    -0.56
    HtmlAttribute
    -0.53
     dand
    -0.51
    UseVisualStyle
    -0.51
     &'
    -0.49
    DebuggerNonUser
    -0.48
    <&
    -0.48
    POSITIVE LOGITS
    :✨
    2.31
     viewDidLoad
    1.16
    /***/
    1.10
    Portail
    1.09
    Transactional
    0.96
    ContentAsync
    0.95
    PerformLayout
    0.91
     tartalomajánló
    0.85
    Serializable
    0.81
     Serializable
    0.79
    Activations Density 0.008%

    No Known Activations