Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 65061
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize connection or interaction with others

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

    connecting with someone or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.58
    Pozri
    -0.57
     ruine
    -0.55
    DockStyle
    -0.54
    NameInMap
    -0.53
     pleadings
    -0.52
    othesis
    -0.52
    ſcher
    -0.52
    ientras
    -0.52
    gorithm
    -0.52
    POSITIVE LOGITS
     CONTACT
    0.54
    contact
    0.54
    Contact
    0.53
     contactar
    0.50
     contacted
    0.49
     contact
    0.49
     Contact
    0.48
     contacto
    0.46
    CONTACT
    0.46
     contacting
    0.42
    Activations Density 0.009%

    No Known Activations