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. 90607
    Prev
    Next
    INDEX
    Explanations

    specific symbols and annotations commonly used in documentation and code comments

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

    query or problem

    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
    orsese
    -0.45
     Exacts
    -0.44
    səhifə
    -0.41
     виправивши
    -0.40
    ソッド
    -0.40
    erçe
    -0.39
    хьтан
    -0.39
     pungkas
    -0.39
    конец
    -0.39
    droj
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.50
    WebElementEntity
    0.49
    OGND
    0.45
    SOUNDBITE
    0.44
     intStringLen
    0.44
     Ohio
    0.41
    countable
    0.41
    AdapterView
    0.41
     Wur
    0.40
     aDecoder
    0.40
    Activations Density 0.000%

    No Known Activations