© 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. 24-GEMMASCOPE-RES-16K
    6. 15998
    Prev
    Next
    INDEX
    Explanations

    details related to programming concepts and function structures

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

    French language tokens and particles

    np_acts-logits-general · gemini-2.0-flash

    Italian/Spanish/French possessives and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.57
     שוליים
    -0.51
     asunder
    -0.50
    исленность
    -0.48
     گوید
    -0.47
    agory
    -0.45
    ltk
    -0.45
    uintptr
    -0.44
    antd
    -0.44
    complexContent
    -0.43
    POSITIVE LOGITS
     del
    2.01
     della
    1.55
     dels
    1.42
     dell
    1.40
    del
    1.29
     delle
    1.25
     dei
    1.23
     de
    1.22
     dello
    1.22
     του
    1.14
    Activations Density 0.062%

    No Known Activations