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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13258
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to mechanical or electrical devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.65
    nthetic
    -0.65
     myſelf
    -0.61
     Meksiku
    -0.61
    tfrac
    -0.58
     Jefus
    -0.56
    esez
    -0.56
    mfrac
    -0.55
    PyExc
    -0.55
     MenuView
    -0.55
    POSITIVE LOGITS
    IContainer
    0.50
     mukaan
    0.48
    NameValuePair
    0.48
    eon
    0.46
    empl
    0.46
    êmio
    0.45
    ennifer
    0.45
    Nvidia
    0.45
     herein
    0.45
     oprot
    0.44
    Activations Density 0.385%

    No Known Activations