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. 7911
    Prev
    Next
    INDEX
    Explanations

    chemical catalysts and their characteristics or effects in reactions

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

    preceding chemical elements or compounds

    np_acts-logits-general · gemini-2.0-flash

    measures parameters for processes

    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
    évaluateur
    -0.46
    AddHtmlAttribute
    -0.39
     ''}
    -0.39
     Vill
    -0.35
    JSONException
    -0.34
    有关
    -0.34
    astify
    -0.34
     censiti
    -0.33
     getNum
    -0.32
     parseFloat
    -0.32
    POSITIVE LOGITS
     gynhyrchwyd
    0.63
    +#+#
    0.59
    SharedCtor
    0.56
     EconPapers
    0.55
    __':
    
    0.55
     consisted
    0.54
     berupa
    0.54
    IndentedString
    0.53
     initComponents
    0.53
     choix
    0.53
    Activations Density 1.463%

    No Known Activations