Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8334
    Prev
    Next
    INDEX
    Explanations

    references to stone materials and specific types of stone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sucesor
    -0.45
    ɵɵelement
    -0.44
    ✨:
    -0.43
     referrerpolicy
    -0.43
     autorytatywna
    -0.43
    ratios
    -0.42
     Tariff
    -0.42
    wijl
    -0.41
    capulco
    -0.41
    ztály
    -0.41
    POSITIVE LOGITS
     stone
    4.19
     Stone
    3.91
    Stone
    3.83
     STONE
    3.70
    stone
    3.34
    STONE
    3.16
     stones
    3.02
     Stones
    2.59
    stones
    2.50
     piedra
    2.44
    Activations Density 0.086%

    No Known Activations