© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5596
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to physics experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -0.92
    LookAnd
    -0.83
    EndProject
    -0.83
    TypedDataSet
    -0.82
    最快更新
    -0.77
     محفوظة
    -0.77
    ExtendWith
    -0.75
    قایناق‌لار
    -0.72
     estekak
    -0.71
     оригіналу
    -0.71
    POSITIVE LOGITS
     pleaf
    0.43
     ticket
    0.42
    áját
    0.41
     '-':
    0.40
    物
    0.40
     spacy
    0.40
     vooraf
    0.39
    дется
    0.38
     tickets
    0.38
     gwiazd
    0.37
    Activations Density 0.450%

    No Known Activations