© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13875
    Prev
    Next
    INDEX
    Explanations

    expressions of criticism or concern regarding media portrayals and public perception

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

    after pronouns

    np_acts-logits-general · gemini-2.0-flash

    his brochures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     Seinfeld
    -0.27
     Règlement
    -0.24
     оп
    -0.24
    Viited
    -0.23
     frequently
    -0.22
    fohl
    -0.21
     explained
    -0.21
     pinched
    -0.21
     parada
    -0.21
     collections
    -0.21
    POSITIVE LOGITS
     EconPapers
    0.83
    httphttps
    0.77
    <unused55>
    0.75
    <unused8>
    0.75
    ſſung
    0.75
    <unused74>
    0.75
    <pad>
    0.75
    <unused14>
    0.74
    <unused3>
    0.74
    [@BOS@]
    0.74
    Activations Density 0.450%

    No Known Activations