© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4038
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations of worth or quality

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

    Phrases indicating impossibility or difficulty

    np_acts-logits-general · gemini-2.0-flash

    cannot be

    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
    NewUrlParser
    -0.48
    évaluateur
    -0.47
     CreateTagHelper
    -0.47
     فريبيس
    -0.47
     Instead
    -0.47
     instead
    -0.45
    principalTable
    -0.44
     lại
    -0.44
    eningen
    -0.44
    
    -0.42
    POSITIVE LOGITS
     cannot
    1.27
     impossible
    1.21
    cannot
    1.16
     couldn
    1.14
     Cannot
    1.14
     impossibility
    1.08
     imposible
    1.06
    Cannot
    1.05
     cant
    1.04
     couldnt
    1.03
    Activations Density 0.219%

    No Known Activations