© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4892
    Prev
    Next
    INDEX
    Explanations

    references to "high" as a descriptor for various qualities or conditions

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

    degree or amount

    np_acts-logits-general · gemini-2.0-flash

    high or higher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.65
    AnchorStyles
    -0.63
    #+#
    -0.60
     composizione
    -0.52
     inalámb
    -0.51
     MacGregor
    -0.51
    oldest
    -0.51
     colectivo
    -0.49
     mús
    -0.48
     Empieza
    -0.48
    POSITIVE LOGITS
     high
    1.12
     HIGH
    1.10
     High
    1.07
    HIGH
    1.06
    high
    1.03
    High
    1.03
     LOW
    0.92
     higher
    0.92
     Low
    0.92
     highest
    0.91
    Activations Density 0.270%

    No Known Activations