© 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. 20-GEMMASCOPE-RES-16K
    11. 15262
    Prev
    Next
    INDEX
    Explanations

    keywords related to e-commerce and online sales strategies

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

    "...channels", "...media", "...technologies"

    np_acts-logits-general · gemini-2.0-flash

    types of media or channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.52
    CppMethod
    -0.46
    hljs
    -0.46
    छे
    -0.45
    Hochspringen
    -0.45
    PhysRevLett
    -0.45
    ">—
    -0.44
    nione
    -0.43
    webpack
    -0.43
     corks
    -0.43
    POSITIVE LOGITS
     channels
    1.41
     mediums
    1.33
     Channels
    1.23
     media
    1.23
     platforms
    1.18
    channels
    1.15
    media
    1.09
    Channels
    1.09
     channel
    1.08
     medium
    1.05
    Activations Density 0.261%

    No Known Activations