© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10794
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a gradual process or action

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

    Adverbs indicating a gradual process

    np_acts-logits-general · gemini-2.0-flash

    slow or gradual change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
     ProtoMessage
    -0.52
    addContainerGap
    -0.50
    ErrUnexpectedEOF
    -0.48
    antastic
    -0.48
     queſta
    -0.46
     wireType
    -0.46
    disambiguation
    -0.46
    RTEX
    -0.46
    ükemmel
    -0.45
     dolayı
    -0.44
    POSITIVE LOGITS
    Slowly
    1.45
     slowly
    1.43
     Slowly
    1.41
     gradually
    1.33
    slowly
    1.27
     Gradually
    1.20
     gradual
    1.15
     perlahan
    1.09
     langsam
    1.06
     lentamente
    1.03
    Activations Density 0.338%

    No Known Activations