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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9250
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent, particularly related to wanting to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    httphttps
    -0.68
    Jîn
    -0.49
     Walkover
    -0.49
    QMetaType
    -0.43
    vindo
    -0.42
    IVEREF
    -0.42
    bkz
    -0.42
     jadx
    -0.41
    GraphicsUnit
    -0.41
    TemporalType
    -0.40
    POSITIVE LOGITS
     wanna
    0.86
    wanna
    0.74
    Wanna
    0.74
     want
    0.72
     chce
    0.70
     wants
    0.69
     Wanna
    0.68
    Хочу
    0.65
     quieren
    0.64
     quiere
    0.64
    Activations Density 0.155%

    No Known Activations