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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 12800
    Prev
    Next
    INDEX
    Explanations

    details and structures pertaining to scientific methods and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.67
    참고
    -0.61
    ChildScrollView
    -0.59
    SharedDtor
    -0.57
    OGND
    -0.55
    RefNanny
    -0.54
    ésult
    -0.54
    AndEndTag
    -0.53
    addContainerGap
    -0.51
     Infórmanos
    -0.51
    POSITIVE LOGITS
    }]);
    0.38
    Eksteraj
    0.35
     Get
    0.35
     Projektu
    0.35
    fehlung
    0.33
    놨
    0.32
    HIDE
    0.32
    ano
    0.31
    ミナル
    0.31
    ίδι
    0.31
    Activations Density 1.095%

    No Known Activations