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. 28-GEMMASCOPE-RES-16K
    6. 4341
    Prev
    Next
    INDEX
    Explanations

    expressions related to programming functions and workflows

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

    Variables/codes followed by symbols

    np_acts-logits-general · gemini-2.0-flash

    technical abbreviations and symbols

    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
     considérons
    -0.36
     cant
    -0.35
    setof
    -0.35
     سكانية
    -0.35
     صوتيه
    -0.34
    匿名使用者
    -0.32
     continúas
    -0.32
    ↵
    -0.32
    なが
    -0.31
    Sat
    -0.31
    POSITIVE LOGITS
     Normdatei
    0.74
    StoryboardSegue
    0.62
    ⟬
    0.58
    pulseira
    0.55
    imageshack
    0.55
    Autoritní
    0.53
    cartão
    0.51
    DataAnnotations
    0.50
     betweenstory
    0.50
    iſen
    0.49
    Activations Density 1.187%

    No Known Activations