© 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. 46868
    Prev
    Next
    INDEX
    Explanations

    expressions of personal relationships and emotional connections

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

    "I" followed by verb

    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
     correctes
    -0.40
     conmigo
    -0.36
     évidemment
    -0.35
     ovviamente
    -0.35
    kwür
    -0.35
    Initially
    -0.34
    kompet
    -0.34
    koliv
    -0.34
     comigo
    -0.33
     pungkas
    -0.33
    POSITIVE LOGITS
     BoxFit
    0.65
     ſta
    0.63
    featureID
    0.60
    modity
    0.60
     ſte
    0.60
    endphp
    0.58
     BorderSide
    0.57
     strerror
    0.55
     ſche
    0.54
    AsUp
    0.52
    Activations Density 0.023%

    No Known Activations