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. 1082
    Prev
    Next
    INDEX
    Explanations

    topics related to economic conditions and their impact on individuals and society

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

    Commas, periods, and "War"

    np_acts-logits-general · gemini-2.0-flash

    imWZ sequence

    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
    izr
    -0.50
    PMailer
    -0.45
     Normdatei
    -0.45
     Lik
    -0.42
    ArgsConstructor
    -0.42
     Mej
    -0.42
    MLLoader
    -0.41
     externi
    -0.41
     ProtoMessage
    -0.40
     Mez
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.53
     CanadaChoose
    0.52
     Comprometido
    0.45
    webElementXpaths
    0.44
     amitié
    0.43
     waarin
    0.43
     kjer
    0.43
     vzduchu
    0.43
     oportunidad
    0.42
     esetben
    0.41
    Activations Density 0.446%

    No Known Activations