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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3360
    Prev
    Next
    INDEX
    Explanations

    phrases related to the capabilities or functions of a system or entity

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

    Sentences starting with "You can" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    ability to perform actions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GEBURTSDATUM
    -0.47
     tend
    -0.40
    featureID
    -0.36
     tap
    -0.36
     AssemblyCompany
    -0.35
     brands
    -0.35
     ceased
    -0.35
    สติ
    -0.34
     was
    -0.33
     fair
    -0.33
    POSITIVE LOGITS
     canst
    0.74
    verwijspagina
    0.71
     can
    0.71
    Can
    0.68
     pouvez
    0.67
     можна
    0.66
    pueden
    0.66
    CanBe
    0.65
     lahko
    0.63
    Puede
    0.62
    Activations Density 2.366%

    No Known Activations