© 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. 11100
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to automotive engineering and technology

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

    Mathematical evaluations or calculations

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions

    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
    Geplaatst
    -0.40
    wußt
    -0.37
    ignées
    -0.37
     pihaknya
    -0.36
    guenos
    -0.35
     romántico
    -0.35
     caído
    -0.35
     habari
    -0.34
     dibujado
    -0.34
    stdc
    -0.33
    POSITIVE LOGITS
     Martyrs
    0.51
     polyps
    0.49
     duster
    0.49
    Datuak
    0.49
     Wembley
    0.48
    WriteAttribute
    0.48
    ########.
    0.47
     gills
    0.47
     Survival
    0.46
     Superhost
    0.46
    Activations Density 0.988%

    No Known Activations