© 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. 16-GEMMASCOPE-RES-16K
    6. 3390
    Prev
    Next
    INDEX
    Explanations

    syntactical elements of programming, particularly those related to function calls and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code paired parentheses/brackets

    np_acts-logits-general · gemini-2.0-flash

    ; ); ] } )

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wood
    -0.56
     Lu
    -0.55
     yet
    -0.54
     Mo
    -0.53
    PLE
    -0.52
    <eos>
    -0.52
     Law
    -0.51
    ukul
    -0.50
    teck
    -0.50
    ple
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    1.10
    setVerticalGroup
    1.01
     فريبيس
    0.96
    expandindo
    0.86
     >=",
    0.82
     صوتيه
    0.80
     bParam
    0.80
    __":
    
    0.79
     myſelf
    0.76
     Савезне
    0.74
    Activations Density 0.175%

    No Known Activations