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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8674
    Prev
    Next
    INDEX
    Explanations

    terms related to modification, alteration, or change, particularly in a legal or coding context

    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
    expandindo
    -0.80
     AssemblyCulture
    -0.75
    Хьажоргаш
    -0.66
     صوتيه
    -0.66
    Personensuche
    -0.65
    bootstrapcdn
    -0.56
     TextAppearance
    -0.56
    RTGC
    -0.55
    SpringBootTest
    -0.54
    parsedMessage
    -0.54
    POSITIVE LOGITS
     modify
    0.91
     alter
    0.82
    modify
    0.81
     modification
    0.80
     alteration
    0.78
    Modify
    0.76
     Modify
    0.75
    alter
    0.70
     amend
    0.68
    Alter
    0.67
    Activations Density 0.276%

    No Known Activations