© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 9716
    Prev
    Next
    INDEX
    Explanations

    memory management references in coding and programming contexts

    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
    use
    -0.53
    Whit
    -0.46
    ("/
    -0.45
    iku
    -0.44
    ="./
    -0.43
     /
    -0.43
    (
    -0.43
    v
    -0.43
    ="/
    -0.43
    using
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    1.41
    enumi
    1.33
    LabelTagHelper
    1.23
    tagHelperRunner
    1.14
    WebControls
    1.11
    __":
    
    1.11
     HasFactory
    1.05
     <<<<<<<<<<<<<<
    1.04
    __':
    
    1.00
    IUrlHelper
    1.00
    Activations Density 0.014%

    No Known Activations