© 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. 22-GEMMASCOPE-RES-16K
    6. 5796
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional services and expertise in health and therapy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.59
    AddTagHelper
    -0.54
     wireType
    -0.53
    guiente
    -0.52
    archiviato
    -0.52
     Normdatei
    -0.52
    itattu
    -0.51
    ">//
    -0.50
    Parcelize
    -0.50
    desenho
    -0.50
    POSITIVE LOGITS
     our
    0.43
     quality
    0.39
     procedure
    0.35
     commitment
    0.33
     offer
    0.32
     Commitment
    0.32
     calidad
    0.32
    quality
    0.32
     offering
    0.31
    我们的
    0.31
    Activations Density 0.095%

    No Known Activations