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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 13576
    Prev
    Next
    INDEX
    Explanations

    programming terms and method names related to API and object manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.72
    ArrowToggle
    -0.72
     SwitchCompat
    -0.72
    Pautan
    -0.65
    DebuggerNonUser
    -0.64
    AntiForgeryToken
    -0.61
     />";
    -0.58
    }>;
    -0.56
    rieu
    -0.56
    LookAnd
    -0.56
    POSITIVE LOGITS
    celes
    0.53
    ⓧ
    0.51
    ImageContext
    0.49
     стать
    0.48
     Overton
    0.46
    NegativeButton
    0.44
    Hozzáférés
    0.44
    uanya
    0.44
    ViewById
    0.44
     cuire
    0.43
    Activations Density 0.053%

    No Known Activations