© 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. 17-GEMMASCOPE-RES-16K
    11. 1397
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and contrasts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exactos
    -0.74
     ویکی‌پدیا
    -0.67
     mergeFrom
    -0.67
     _$
    -0.58
     ControllerBase
    -0.55
    ndose
    -0.53
    awtextra
    -0.53
    voerd
    -0.51
     resourceCulture
    -0.51
    tings
    -0.49
    POSITIVE LOGITS
     hingegen
    1.24
     наоборот
    1.23
     invece
    1.22
     dagegen
    1.13
    則是
    1.04
     justru
    1.00
    則
    0.97
     simpler
    0.95
     sebaliknya
    0.92
    则
    0.91
    Activations Density 1.169%

    No Known Activations