© 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. 28-GEMMASCOPE-RES-16K
    6. 3893
    Prev
    Next
    INDEX
    Explanations

    specific references to exams and related procedural inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Questions about remainders, factors, or multiples

    np_acts-logits-general · gemini-2.0-flash

    SAT score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.52
    büro
    -0.46
    GEBURTSDATUM
    -0.46
    AddTagHelper
    -0.45
    $_['
    -0.45
     jScrollPane
    -0.45
    holdet
    -0.43
    sizeCache
    -0.42
     atividade
    -0.42
     snippetHide
    -0.42
    POSITIVE LOGITS
    考生
    0.55
     aspirants
    0.52
     Candidates
    0.51
     Aspir
    0.49
     candidates
    0.49
     exam
    0.46
    andidates
    0.46
    centiles
    0.45
     Exam
    0.45
     betweenstory
    0.45
    Activations Density 0.125%

    No Known Activations