© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14441
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to data communication protocols

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

    logical connectors like "therefore" that indicate causality or conclusion, often appearing before commas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Савезне
    -0.52
    gih
    -0.45
    weil
    -0.43
    however
    -0.42
    Gilla
    -0.41
    cyk
    -0.41
     however
    -0.40
     ModelRenderer
    -0.40
     však
    -0.39
     übrigens
    -0.39
    POSITIVE LOGITS
    routeProvider
    0.50
    MessageOf
    0.43
    enterOuterAlt
    0.38
    shadowRadius
    0.35
    AndroidJUnit
    0.35
    rawDesc
    0.34
     basically
    0.34
     he
    0.33
     UIApplication
    0.33
    HasColumnType
    0.33
    Activations Density 0.823%

    No Known Activations