© 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. 16-GEMMASCOPE-RES-16K
    6. 13075
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs indicating actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.71
    setViewportView
    -0.66
     ujednoznacz
    -0.60
     pinulongan
    -0.58
    ChildScrollView
    -0.58
     nakalista
    -0.58
    yntaxException
    -0.56
     ProtoMessage
    -0.56
    Життєпис
    -0.55
     المعيارى
    -0.54
    POSITIVE LOGITS
     therefore
    0.47
     hivyo
    0.39
     mikä
    0.37
    therefore
    0.36
     así
    0.35
     asegur
    0.35
    和
    0.34
    essentiel
    0.33
     kautta
    0.33
    かつ
    0.33
    Activations Density 0.286%

    No Known Activations