© 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. 28-GEMMASCOPE-RES-16K
    11. 3405
    Prev
    Next
    INDEX
    Explanations

    discussions and actions related to involvement, engagement, and decision-making processes, especially in contexts involving research and communication

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

    followed by "directly"

    np_acts-logits-general · gemini-2.0-flash

    direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.42
    ViewImports
    -0.39
    Compatible
    -0.38
    [][]
    -0.36
     Normdatei
    -0.36
    aku
    -0.35
    illus
    -0.34
    #+#
    -0.34
    ictwo
    -0.34
    ANTLR
    -0.34
    POSITIVE LOGITS
     directly
    2.53
     direct
    2.42
    directly
    2.39
     Directly
    2.28
    直接
    2.25
     directamente
    2.19
     directement
    2.17
    direct
    2.13
    Direct
    2.08
     direttamente
    2.05
    Activations Density 1.088%

    No Known Activations