© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or sentence-ending indicators

    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
    Bibliograf
    -0.43
     puder
    -0.39
     Resultados
    -0.38
     veranderen
    -0.36
    Gew
    -0.36
     hardly
    -0.35
    BackgroundImage
    -0.35
     considered
    -0.34
     able
    -0.34
     tarko
    -0.33
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     disambiguazione
    0.66
    MessageOf
    0.63
    omitempty
    0.61
    delwed
    0.59
    MLLoader
    0.58
    onAttach
    0.58
     consultato
    0.56
    HasForeignKey
    0.55
     oprot
    0.55
    Activations Density 0.988%

    No Known Activations