© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6015
    Prev
    Next
    INDEX
    Explanations

    terms related to defense and aerospace industries

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

    Follows numbers or IDs (e.g., F-15, Lockheed U-2)

    np_acts-logits-general · gemini-2.0-flash

    F-15 F-14 Aerodynamic data

    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
     '\\;'
    -0.64
     ब्रेकडाउन
    -0.56
    WebElementEntity
    -0.55
    #+#
    -0.50
    RegressionTest
    -0.47
    mapbox
    -0.44
     RemoteException
    -0.42
    verwijspagina
    -0.41
    ANTLR
    -0.41
    ⟬
    -0.41
    POSITIVE LOGITS
    portál
    0.53
     Wicidata
    0.44
    umman
    0.43
    Diweddarwch
    0.38
     consign
    0.38
     liso
    0.37
    出版年
    0.37
    UrlResolution
    0.36
    зец
    0.36
     prototypes
    0.35
    Activations Density 0.334%

    No Known Activations