© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6916
    Prev
    Next
    INDEX
    Explanations

    references to serialized data structures and event arguments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.66
    Krok
    -0.59
    BeginInit
    -0.55
    iseks
    -0.54
    IMPORTED
    -0.53
    MathML
    -0.53
    TagMode
    -0.51
     Balboa
    -0.51
    DebuggerNonUser
    -0.51
    ValueStyle
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    1.36
     EventArgs
    1.33
    WriteLiteral
    1.16
    ViewHolder
    1.09
     InputDecoration
    1.03
    EditText
    1.00
    MessageTagHelper
    0.97
     protoimpl
    0.94
     initComponents
    0.92
     propOrder
    0.89
    Activations Density 0.010%

    No Known Activations