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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6665
    Prev
    Next
    INDEX
    Explanations

    information related to software versions and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.67
    ométrique
    -0.65
    tagHelperRunner
    -0.62
     سكانية
    -0.60
    Personendaten
    -0.57
    ComponentScan
    -0.57
    OGND
    -0.57
    
    -0.56
    MockBean
    -0.56
     Thought
    -0.56
    POSITIVE LOGITS
    inch
    0.59
    ficit
    0.58
    bộ
    0.57
    +#+
    0.57
     kaynağından
    0.55
     shore
    0.55
    CORO
    0.53
    版本的
    0.53
    tagHelper
    0.52
    :+:
    0.52
    Activations Density 2.341%

    No Known Activations