© 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. 18-GEMMASCOPE-RES-16K
    6. 6901
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to conditional statements and case handling in programming

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

    Cases/defaults/fallbacks within switch/case statements

    np_acts-logits-general · gemini-2.0-flash

    case statements with let bindings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     congratulations
    -1.23
     Congratulations
    -1.06
     congrats
    -1.05
    Congratulations
    -1.05
     congratulate
    -0.96
     Congrats
    -0.96
    Congrats
    -0.95
    congratulations
    -0.92
     congrat
    -0.82
    congrats
    -0.81
    POSITIVE LOGITS
     _
    1.06
     _,
    1.03
    (_
    0.91
    _,
    0.89
    ,_
    0.87
     *_
    0.84
    [_
    0.83
     _)
    0.82
     [_
    0.77
     &_
    0.76
    Activations Density 0.197%

    No Known Activations