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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7783
    Prev
    Next
    INDEX
    Explanations

    elements related to item specifications and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kautta
    -0.45
     spørgsmål
    -0.44
     lisäksi
    -0.44
     jopa
    -0.40
     vœ
    -0.40
     spørsmål
    -0.40
     erity
    -0.40
     aihe
    -0.39
     only
    -0.39
     jornadas
    -0.39
    POSITIVE LOGITS
    PyExc
    0.79
    󠁣
    0.78
    󠁴
    0.75
     ModelExpression
    0.72
    QMetaType
    0.72
    NameInMap
    0.69
    RegistryLite
    0.68
     kaarangay
    0.68
     jadx
    0.67
     Italijani
    0.66
    Activations Density 1.039%

    No Known Activations