© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8071
    Prev
    Next
    INDEX
    Explanations

    mentions of relevance or pertinent information

    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
    LayoutPanel
    -0.93
    BeginContext
    -0.85
    TypedDataSet
    -0.82
    Personensuche
    -0.80
    AnchorStyles
    -0.71
    AndEndTag
    -0.69
     CreateTagHelper
    -0.69
    douard
    -0.69
    webElementXpaths
    -0.68
     PSM
    -0.67
    POSITIVE LOGITS
    LEVANT
    1.50
     relevant
    1.46
    Relevant
    1.40
    relevant
    1.38
     Relevant
    1.32
    levance
    1.30
     Relevance
    1.25
    Relevance
    1.24
     relevan
    1.20
     pertinent
    1.20
    Activations Density 0.099%

    No Known Activations