© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2011
    Prev
    Next
    INDEX
    Explanations

    relationships between groups and shared characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.58
    __":
    -0.42
    posedge
    -0.41
    QMetaType
    -0.40
    Personendaten
    -0.40
    ACHUSET
    -0.39
    Gambas
    -0.39
    тябрь
    -0.38
    writeFieldEnd
    -0.38
    MessageTagHelper
    -0.38
    POSITIVE LOGITS
     common
    3.70
    common
    3.20
     Common
    2.97
    Common
    2.89
     COMMON
    2.84
    COMMON
    2.67
     común
    2.52
     comunes
    2.42
    共通
    2.39
     comum
    2.38
    Activations Density 1.707%

    No Known Activations