Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 536
    Prev
    Next
    INDEX
    Explanations

    unit measurements and concentrations related to substances and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.61
    aways
    -0.56
    able
    -0.47
    っぱ
    -0.46
     immun
    -0.46
    スタ
    -0.46
    ables
    -0.45
     close
    -0.45
    หลัก
    -0.44
     사
    -0.43
    POSITIVE LOGITS
    DockStyle
    1.20
    脚注の使い方
    1.10
     HasFactory
    1.07
    AndEndTag
    0.91
    CloseOperation
    0.87
     BoxDecoration
    0.86
    mybatisplus
    0.84
     onCreateView
    0.83
     AttributeSet
    0.80
    IntoConstraints
    0.80
    Activations Density 0.269%

    No Known Activations