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. 21-GEMMASCOPE-RES-16K
    6. 7246
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terminology related to technology and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }>;
    -0.63
    angé
    -0.53
    AddTagHelper
    -0.53
     noten
    -0.51
    ādā
    -0.49
    แค่
    -0.47
    roscope
    -0.47
    बस
    -0.45
    ?).
    -0.45
    upsi
    -0.45
    POSITIVE LOGITS
     widely
    1.06
     Recently
    0.97
     Lately
    0.96
     recently
    0.95
     широко
    0.95
    Recently
    0.95
     Widely
    0.94
    InjectAttribute
    0.94
    recently
    0.94
    近年
    0.90
    Activations Density 1.570%

    No Known Activations