© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2962
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical data

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

    code structure and programming syntax, particularly programming control flow keywords like 'if', 'else', 'return', and code block markers like '{' and '}'.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    
    -1.26
     autorytatywna
    -1.23
    niſſe
    -1.20
     ujednoznacz
    -1.18
    ſſung
    -1.17
    ⟬
    -1.16
    iſchen
    -1.15
    BeginContext
    -1.13
    ConstraintMaker
    -1.13
     disambiguazione
    -1.12
    POSITIVE LOGITS
    ↵↵
    0.76
    .
    0.70
    1
    0.55
     
    0.54
    </table>
    0.51
    ↵↵↵↵
    0.51
    ↵↵↵
    0.49
    -
    0.45
    4
    0.44
    }
    0.44
    Activations Density 0.142%

    No Known Activations