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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 98011
    Prev
    Next
    INDEX
    Explanations

    terms related to financial agreements and transactions, particularly concerning promissory notes and assignments

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

    assignments of error, notes, stock

    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
     referenties
    -0.39
     compat
    -0.36
    makeText
    -0.34
    ukone
    -0.33
     compli
    -0.32
     quer
    -0.31
     ​​
    -0.31
    Handlung
    -0.31
     incompati
    -0.30
     gynhyrchwyd
    -0.30
    POSITIVE LOGITS
    GEBUR
    0.50
     wikipagina
    0.49
     AsyncTask
    0.48
     jurk
    0.46
    GTCX
    0.46
    şekkür
    0.45
     abstrato
    0.45
     touristes
    0.44
    collana
    0.44
    DataSnapshot
    0.44
    Activations Density 0.121%

    No Known Activations