© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 6603
    Prev
    Next
    INDEX
    Explanations

    specific biochemical terms related to angiotensin and its functions

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

    angiotensin and orcid

    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
     disambiguazione
    -0.49
    ollectionView
    -0.49
     deserved
    -0.48
     Alfaro
    -0.47
    gesch
    -0.47
    aim
    -0.47
    homonymie
    -0.46
     prat
    -0.45
     forgotten
    -0.44
    würdigkeiten
    -0.43
    POSITIVE LOGITS
    putnik
    0.94
    jsii
    0.88
     Sputnik
    0.79
     protoimpl
    0.77
    Personensuche
    0.69
    iotensin
    0.55
    Werner
    0.50
    eezy
    0.50
     sputnik
    0.49
    wapV
    0.48
    Activations Density 0.009%

    No Known Activations