© 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. 2-GEMMASCOPE-RES-16K
    6. 8689
    Prev
    Next
    INDEX
    Explanations

    phrases related to chemical compounds and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.46
     prédé
    -0.41
    Sklici
    -0.40
     autorité
    -0.40
     Bombs
    -0.39
    BufferException
    -0.39
     woorden
    -0.39
     médicament
    -0.39
     libéral
    -0.38
     serangan
    -0.38
    POSITIVE LOGITS
     compound
    0.79
     Compound
    0.73
    compound
    0.73
     cheer
    0.67
    Compound
    0.66
     COMPOUND
    0.65
     cabin
    0.62
     compounds
    0.61
    Chunk
    0.60
    sidemargin
    0.59
    Activations Density 0.253%

    No Known Activations