© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10567
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly in a range or context related to data analysis

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

    The number 13

    np_acts-logits-general · gemini-2.0-flash

    the number thirteen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gorilla
    -0.44
     smoothie
    -0.43
     Moisture
    -0.41
     profitably
    -0.41
     desirability
    -0.41
     Camel
    -0.40
    Carriera
    -0.40
    arangay
    -0.40
    Moisture
    -0.40
    良かったです
    -0.40
    POSITIVE LOGITS
    ruptedException
    0.67
    Thirteen
    0.65
    UNRELATED
    0.65
     thirteen
    0.63
     Thirteen
    0.62
    XIII
    0.61
     thirteenth
    0.61
    onAttach
    0.60
    Personendaten
    0.59
     XIII
    0.56
    Activations Density 0.271%

    No Known Activations