© 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. 24-GEMMASCOPE-RES-16K
    11. 6237
    Prev
    Next
    INDEX
    Explanations

    references to mountains and their geographical or environmental context

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

    like "mountain", "alpine", or "altitude"

    np_acts-logits-general · gemini-2.0-flash

    mountains and alpine regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.50
    UrlResolution
    -0.49
    WebServlet
    -0.45
     Baghdad
    -0.44
     GreatSchools
    -0.43
     Halley
    -0.41
    ">//
    -0.41
    TypedDataSet
    -0.41
     Gaza
    -0.40
    OCCURRED
    -0.40
    POSITIVE LOGITS
     mountain
    1.14
     Mountain
    1.08
    Mountain
    1.06
     mountaine
    1.05
    mountain
    1.03
     mountains
    1.02
     mountainous
    0.99
     Mountains
    0.98
    Mountains
    0.94
    🏔
    0.91
    Activations Density 0.827%

    No Known Activations