© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3280
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to genetics and microbial resistance

    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
    Resta
    -0.59
    OGND
    -0.56
     ostavi
    -0.56
     transférez
    -0.54
    AddTagHelper
    -0.53
     trùng
    -0.52
     ser
    -0.52
     lucr
    -0.51
     FormBuilder
    -0.50
     rozwo
    -0.50
    POSITIVE LOGITS
    Erstellt
    0.64
    didSet
    0.60
     poem
    0.60
    adə
    0.58
     TextFormField
    0.58
     Paglinawan
    0.57
    bootstrapcdn
    0.57
     Hallo
    0.55
    rolid
    0.55
    usercontent
    0.54
    Activations Density 3.183%

    No Known Activations