© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 37127
    Prev
    Next
    INDEX
    Explanations

    the preposition "in," indicating locations or contextual inclusions

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

    in [money or quantity]

    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
    AutoScaleMode
    -0.50
    abstractmethod
    -0.40
    PointerException
    -0.38
     Warte
    -0.38
     religión
    -0.38
     meubles
    -0.36
     caracteriza
    -0.35
    fritt
    -0.35
     ViewPager
    -0.35
     expérimentés
    -0.35
    POSITIVE LOGITS
    enumi
    0.56
    csolódó
    0.54
    urp
    0.51
     hinweg
    0.51
     мәкал
    0.50
    atified
    0.50
     Efq
    0.50
    rui
    0.48
    avax
    0.48
    期刊论文
    0.48
    Activations Density 0.012%

    No Known Activations