© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8338
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly in relation to the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -1.20
    )\}$
    -0.85
    yczą
    -0.85
     ModelRenderer
    -0.85
     Pixie
    -0.83
     Mercure
    -0.83
     Woodbury
    -0.82
    }\}$
    -0.81
    Datuak
    -0.81
     Oakley
    -0.81
    POSITIVE LOGITS
     last
    2.07
     LAST
    1.86
    last
    1.85
     Last
    1.83
    Last
    1.79
    LAST
    1.78
    setLast
    1.42
    getLast
    1.35
     getLast
    1.34
     último
    1.29
    Activations Density 0.059%

    No Known Activations