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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15737
    Prev
    Next
    INDEX
    Explanations

    keywords and elements related to database interactions and web development structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.59
     acuerdo
    -0.47
     perang
    -0.46
     JMenuItem
    -0.46
    CodeAttribute
    -0.44
     свете
    -0.44
    กรม
    -0.44
    Personensuche
    -0.44
    veux
    -0.43
     compromisos
    -0.43
    POSITIVE LOGITS
     nakalista
    0.85
    XmlAccessType
    0.83
    InputTagHelper
    0.74
    SequentialGroup
    0.73
     toy
    0.68
    AndroidJUnit
    0.65
    toy
    0.65
     CreateTagHelper
    0.65
    GroupLayout
    0.65
     Thessal
    0.63
    Activations Density 1.667%

    No Known Activations