© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 111195
    Prev
    Next
    INDEX
    Explanations

    expressions of praise and personal sentiment

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

    unconditional, overflowing, showered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     favorable
    -0.62
     beneficial
    -0.60
     favourable
    -0.58
     advantageous
    -0.58
     favorables
    -0.57
    Попис
    -0.55
     Vorteil
    -0.55
    ValueStyle
    -0.54
    favorable
    -0.54
     pleaſure
    -0.53
    POSITIVE LOGITS
     unconditional
    0.57
     overflowing
    0.56
     showered
    0.50
     unqualified
    0.50
    typeorm
    0.46
     overdo
    0.45
     Overflow
    0.44
     showering
    0.44
     unconditionally
    0.43
     genuine
    0.43
    Activations Density 0.051%

    No Known Activations