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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1934
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and decision-making

    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
    SequentialGroup
    -0.68
     <<<<<<<<<<<<<<
    -0.61
     Chwiliwch
    -0.59
    ChildScrollView
    -0.58
    ściej
    -0.55
    arid
    -0.55
     كومونز
    -0.51
    género
    -0.51
    stdc
    -0.50
    ropo
    -0.50
    POSITIVE LOGITS
     zoals
    1.25
     how
    1.24
     exactly
    1.19
     όπως
    1.11
     whatever
    1.08
     however
    1.08
     ahogy
    1.08
     sebagaimana
    1.08
    exactly
    1.01
     EXACTLY
    0.96
    Activations Density 0.291%

    No Known Activations