© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8200
    Prev
    Next
    INDEX
    Explanations

    the term "remaining" in various contexts, indicating a focus on quantities left over or still present

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.60
    BASEPATH
    -0.54
    contentLoaded
    -0.52
    QMetaType
    -0.50
     OFDb
    -0.49
    confidence
    -0.46
     confidence
    -0.46
     exits
    -0.46
     Shots
    -0.45
    XMLSchema
    -0.44
    POSITIVE LOGITS
     remaining
    1.41
    Remaining
    1.32
    remaining
    1.31
     residual
    1.29
     Remaining
    1.19
     leftover
    1.18
     residue
    1.08
     Residual
    1.05
    Leave
    1.05
     leftovers
    1.04
    Activations Density 0.147%

    No Known Activations