© 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. 14-GEMMASCOPE-RES-16K
    6. 8695
    Prev
    Next
    INDEX
    Explanations

    structures and formatting elements typically found in technical documents or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.42
     modernos
    -0.34
     moderna
    -0.34
    ログ
    -0.33
     modernas
    -0.32
    sodik
    -0.31
     Judd
    -0.30
    izde
    -0.30
     modernes
    -0.30
    押し
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.80
    CloseOperation
    0.73
    KommentareTeilen
    0.69
     GenerationType
    0.69
    IsContent
    0.66
    principalTable
    0.63
    Personensuche
    0.59
    StoryboardSegue
    0.59
    NameInMap
    0.59
     مشين
    0.58
    Activations Density 0.352%

    No Known Activations