© 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. 15-GEMMASCOPE-RES-16K
    11. 1290
    Prev
    Next
    INDEX
    Explanations

    contextual phrases related to limitations and effectiveness in a study or experimental setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.53
    adə
    -0.48
    خار
    -0.47
    OrEqual
    -0.47
     dynasties
    -0.47
    onoi
    -0.46
    WriteAttribute
    -0.45
     ویکی‌پدیا
    -0.44
    INCLUDED
    -0.44
     digna
    -0.44
    POSITIVE LOGITS
     незавершена
    1.04
     relatively
    0.74
    あくまで
    0.71
     Relatively
    0.65
    };*/
    0.64
     predominantly
    0.64
    complexType
    0.64
    あく
    0.63
    relatively
    0.62
     older
    0.61
    Activations Density 0.397%

    No Known Activations