© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2338
    Prev
    Next
    INDEX
    Explanations

    terms related to description and evaluation

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

    Modal verbs or auxiliary verbs used in descriptive phrases (specifically "can," "be," and "would").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ErrorListener
    -0.34
    XtraReports
    -0.31
     RoutedEventArgs
    -0.29
    舺
    -0.28
    __":
    -0.27
     segnale
    -0.25
     MonoBehaviour
    -0.25
    튀
    -0.25
    setopt
    -0.24
    titions
    -0.24
    POSITIVE LOGITS
     description
    2.36
     describe
    2.23
     described
    2.14
     descriptions
    2.14
     describes
    2.09
     describing
    1.98
     describir
    1.93
     Description
    1.91
    description
    1.88
     DESCR
    1.88
    Activations Density 0.470%

    No Known Activations