© 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. 9-GEMMASCOPE-RES-131K
    6. 4960
    Prev
    Next
    INDEX
    Explanations

    mentions of streets in various contexts

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

    street names and addresses

    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
    뀜
    -0.37
    BufferException
    -0.37
     wakil
    -0.36
    haustible
    -0.36
    ьаж
    -0.35
     zasi
    -0.35
     widerrufen
    -0.35
     dikenal
    -0.35
     uns
    -0.34
    дых
    -0.33
    POSITIVE LOGITS
     Street
    2.30
    Street
    2.05
     STREET
    1.88
    street
    1.51
    STREET
    1.48
     street
    1.45
     Streets
    1.40
    Streets
    1.23
    streets
    1.13
    ストリート
    1.05
    Activations Density 0.005%

    No Known Activations