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. 1969
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and programming elements such as functions and formatting directives

    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
    laszt
    -0.58
     drinking
    -0.52
    RetentionPolicy
    -0.49
     udaler
    -0.49
    LoadScene
    -0.45
     jspb
    -0.45
    imakasih
    -0.44
    BarStyle
    -0.44
    ◀
    -0.44
     noDo
    -0.44
    POSITIVE LOGITS
    findpost
    0.67
    IsContent
    0.66
    StoreMessageInfo
    0.63
     AUTHORITY
    0.60
     виправивши
    0.59
    }),
    
    0.58
    getMinutes
    0.57
    const
    0.57
     ujednoznacz
    0.56
     hidráulica
    0.53
    Activations Density 0.020%

    No Known Activations