© 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. 1-GEMMASCOPE-RES-16K
    6. 3073
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe the composition or structure of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.46
    homonymie
    -0.45
     lapangan
    -0.44
     maternidade
    -0.43
     AÑOS
    -0.41
    UseVisualStyle
    -0.41
     SCHEME
    -0.41
     muerte
    -0.41
    bewerken
    -0.41
     abogados
    -0.41
    POSITIVE LOGITS
     consisted
    1.58
     consist
    1.52
     consists
    1.38
     comprised
    1.37
     consisting
    1.34
     constituted
    1.21
     comprise
    1.19
     constitute
    1.14
     comprises
    1.09
     constitutes
    1.05
    Activations Density 0.186%

    No Known Activations