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. 3-GEMMASCOPE-RES-16K
    6. 12414
    Prev
    Next
    INDEX
    Explanations

    references to open-source projects and discussions surrounding open-source software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.96
    VIAF
    -0.87
     defaultstate
    -0.84
    GraphicsUnit
    -0.82
    Obrázky
    -0.82
    AddTagHelper
    -0.81
    IsMutable
    -0.80
    DeleteBehavior
    -0.80
    soever
    -0.80
    脚注の使い方
    -0.79
    POSITIVE LOGITS
    npmjs
    0.47
    orn
    0.46
     des
    0.45
    alet
    0.44
     dis
    0.43
     pe
    0.43
     pod
    0.43
    نم
    0.42
     war
    0.42
    esy
    0.42
    Activations Density 0.770%

    No Known Activations