© 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. 31-GEMMASCOPE-RES-16K
    11. 9498
    Prev
    Next
    INDEX
    Explanations

    positive experiences or sentiments related to specific topics or subjects

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

    superlative phrases expressing positive or negative evaluation (e.g., "best thing," "nice thing," "frustrating thing," "wonderful thing").

    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
    XmlRootElement
    -0.41
    Hauptartikel
    -0.40
    Personendaten
    -0.39
    麓
    -0.37
    needed
    -0.37
    endpush
    -0.36
    請繼續往下閱讀
    -0.36
    SerializeField
    -0.36
    品です
    -0.36
     Stans
    -0.35
    POSITIVE LOGITS
     about
    1.19
     aspect
    1.10
     part
    0.90
    aspect
    0.85
    about
    0.84
     aspects
    0.82
    aspects
    0.78
     Aspect
    0.77
    About
    0.76
     thing
    0.73
    Activations Density 0.161%

    No Known Activations