© 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. 5-GEMMASCOPE-RES-16K
    6. 6454
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases that indicate a need for clarification or specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.75
    ungsbedingungen
    -0.60
     raising
    -0.58
     Dinge
    -0.50
    Granite
    -0.50
    GroupLayout
    -0.49
     Agnew
    -0.49
     Tripod
    -0.49
     Granite
    -0.49
    비
    -0.48
    POSITIVE LOGITS
     Which
    1.24
    Which
    1.20
     کدام
    1.10
     Welche
    1.09
     hangi
    1.06
     welk
    1.05
    hichever
    1.04
    哪个
    0.98
    Welke
    0.96
    どの
    0.95
    Activations Density 0.089%

    No Known Activations