© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7689
    Prev
    Next
    INDEX
    Explanations

    elements related to setting and location in narratives

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

    Prepositions/articles followed by locations

    np_acts-logits-general · gemini-2.0-flash

    places and geographical locations

    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
    tagHelperRunner
    -0.54
     صوتيه
    -0.50
    XmlAccessorType
    -0.49
     المعيارى
    -0.49
     ProtoMessage
    -0.46
     henvisninger
    -0.45
    NamedQueries
    -0.45
    WillAppear
    -0.44
    WriteTagHelper
    -0.43
    ksikon
    -0.43
    POSITIVE LOGITS
     streets
    0.75
     city
    0.71
     mountains
    0.70
     oceans
    0.66
     beaches
    0.64
     caves
    0.64
     forests
    0.64
     deserts
    0.64
     suburb
    0.64
     suburbs
    0.63
    Activations Density 0.796%

    No Known Activations