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. 23-GEMMASCOPE-RES-16K
    6. 8924
    Prev
    Next
    INDEX
    Explanations

    code structure and elements used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.76
    IsMutable
    -0.66
    +#+#
    -0.64
    
    -0.64
     fieldNum
    -0.64
    protoimpl
    -0.62
    featureID
    -0.62
     متعلقه
    -0.61
    ⓧ
    -0.60
    oa̍t
    -0.59
    POSITIVE LOGITS
    getApplication
    1.12
     getApplication
    1.01
    getBase
    0.86
     getBase
    0.76
     application
    0.71
    activity
    0.69
     AppCompat
    0.69
     getActivity
    0.68
     activity
    0.68
    application
    0.67
    Activations Density 0.066%

    No Known Activations