© 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. 10-GEMMASCOPE-RES-16K
    11. 4350
    Prev
    Next
    INDEX
    Explanations

    references to specific products or services, particularly related to storage facilities and dating services in Milton-Freewater

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.83
    TestingModule
    -0.70
    ftagPool
    -0.69
    iprot
    -0.67
     protoimpl
    -0.67
    styleType
    -0.63
    InvalidProtocol
    -0.61
    ValueStyle
    -0.61
    Jereo
    -0.60
    NameInMap
    -0.60
    POSITIVE LOGITS
     MonoBehaviour
    0.63
    ⓘ
    0.50
    xsi
    0.47
     يتيمه
    0.44
    alk
    0.44
    versorgung
    0.43
    untitled
    0.43
    hir
    0.43
    veren
    0.42
     apost
    0.42
    Activations Density 0.130%

    No Known Activations