© 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. 18-GEMMASCOPE-RES-16K
    11. 9656
    Prev
    Next
    INDEX
    Explanations

    references to academic authors, research papers, or scientific citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Initial of first or last name

    np_acts-logits-general · gemini-2.0-flash

    Economic Studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.86
    بوابة
    -0.76
    SourceChecksum
    -0.63
    Hozzáférés
    -0.60
    
    -0.60
     kaarangay
    -0.60
    ोर्ट
    -0.58
     zure
    -0.54
    lemény
    -0.54
    NamedQuery
    -0.53
    POSITIVE LOGITS
    lidene
    0.53
     DMR
    0.48
     Skinny
    0.46
     concetto
    0.46
    TagHelpers
    0.46
     TextInputType
    0.45
     QtCore
    0.45
     RM
    0.45
     MBR
    0.45
    MBR
    0.45
    Activations Density 0.601%

    No Known Activations