Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1035
    Prev
    Next
    INDEX
    Explanations

    place names and geographic locations

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

    ending in "ville", "onga", "assa", or "romi"

    np_acts-logits-general · gemini-2.0-flash

    place names ending in ville or ster

    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
     Birmingham
    -0.53
     Genève
    -0.50
     Dublin
    -0.50
    Birmingham
    -0.50
    Brisbane
    -0.49
     Denver
    -0.49
     Kraków
    -0.48
    benhavn
    -0.47
     Brisbane
    -0.47
     Chennai
    -0.47
    POSITIVE LOGITS
    ocino
    0.48
     sheriff
    0.44
    Portale
    0.42
     Sheriff
    0.42
    scriptcase
    0.41
     river
    0.41
    ValueStyle
    0.41
    ValuePair
    0.40
    Sheriff
    0.39
     VF
    0.38
    Activations Density 0.409%

    No Known Activations