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. 65115
    Prev
    Next
    INDEX
    Explanations

    references to partnerships and their dissolution

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

    partnership related terms

    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
     Picchu
    -0.43
     يتيمه
    -0.38
     ירושלים
    -0.35
     sarili
    -0.34
    tvguidetime
    -0.33
    calciatore
    -0.32
    стракт
    -0.32
    anella
    -0.32
    siasme
    -0.32
    idee
    -0.32
    POSITIVE LOGITS
    
    0.59
     muſt
    0.57
     Houſe
    0.55
     tartalomajánló
    0.54
    TypedDataSet
    0.52
     Signalez
    0.51
     Partnership
    0.51
     partnership
    0.50
    ExecuteReader
    0.50
     ſhall
    0.50
    Activations Density 0.086%

    No Known Activations