© 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
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6091
    Prev
    Next
    INDEX
    Explanations

    technical processes and components related to systems and algorithms

    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
     avoient
    -0.68
     prêtres
    -0.65
     étoient
    -0.63
     démocr
    -0.62
    wasn
    -0.59
     chrétiens
    -0.57
     wasn
    -0.57
     ferons
    -0.56
     cérami
    -0.55
     vectorielles
    -0.55
    POSITIVE LOGITS
     models
    0.57
    SharedCtor
    0.55
     fashions
    0.54
     prototypes
    0.51
    WebControls
    0.51
     designs
    0.51
     protoimpl
    0.49
     profiles
    0.49
    posedge
    0.49
     engineers
    0.48
    Activations Density 0.732%

    No Known Activations