© 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. 31-GEMMASCOPE-RES-16K
    6. 670
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate significance or importance in various contexts

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

    phrases structured as "[noun] is a [adjective/descriptive phrase]" that make emphatic statements or characterizations.

    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
    تقاوى
    -0.59
    الحياه
    -0.55
    Autoritní
    -0.53
     <<<<<<<<<<<<<<
    -0.48
     ویکی‌پدی
    -0.48
    
    -0.48
    tagHelperRunner
    -0.48
     nakalista
    -0.47
     ویکی‌پدیا
    -0.47
    XmlAccessorType
    -0.46
    POSITIVE LOGITS
     proof
    2.48
     evidence
    2.02
     Proof
    1.98
    proof
    1.92
    Proof
    1.90
     preuve
    1.73
    evidence
    1.70
     testimony
    1.68
     PROOF
    1.63
     Evidence
    1.59
    Activations Density 0.344%

    No Known Activations