© 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. 28-GEMMASCOPE-RES-16K
    6. 4571
    Prev
    Next
    INDEX
    Explanations

    instances of the word "often" or similar variants indicating frequency

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

    frequency or occurrence

    np_acts-logits-general · gemini-2.0-flash

    often, sometimes, frequently

    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
     Autorizaciones
    -0.53
     nigdy
    -0.41
     inspiradoras
    -0.41
     setEmail
    -0.40
    yelidikan
    -0.40
     desar
    -0.40
     intptr
    -0.39
     flesta
    -0.39
    ConstraintMaker
    -0.37
     hoga
    -0.37
    POSITIVE LOGITS
     бывает
    0.60
    times
    0.54
     приходится
    0.53
    jména
    0.52
     times
    0.52
    KommentareTeilen
    0.50
     mukana
    0.50
     genug
    0.49
    /**
    0.49
    __(/*!
    0.48
    Activations Density 0.124%

    No Known Activations