© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    references to alternative options or components

    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
     كومونز
    -0.54
     kind
    -0.51
     sort
    -0.51
     miniaturka
    -0.46
     mere
    -0.45
     Inscrivez
    -0.45
     garansi
    -0.44
     onOptions
    -0.44
    Kind
    -0.44
     perkara
    -0.44
    POSITIVE LOGITS
    Somehow
    0.61
     sometime
    0.60
    Somewhere
    0.55
     Sometime
    0.54
     Somehow
    0.54
     Somewhere
    0.52
    Something
    0.48
     somewhere
    0.48
    somewhere
    0.45
     rivista
    0.45
    Activations Density 0.211%

    No Known Activations