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. 16-GEMMASCOPE-RES-16K
    6. 14804
    Prev
    Next
    INDEX
    Explanations

    affirmations or indications of significance and continuity within societal or cultural contexts

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

    proof/evidence

    np_acts-logits-general · gemini-2.0-flash

    shows demonstrates highlights testament

    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
     raiſ
    -0.75
     quæ
    -0.74
     pleaſure
    -0.72
     myſelf
    -0.72
     Jefus
    -0.72
     ſeveral
    -0.69
     ſta
    -0.67
     ſte
    -0.67
     ſever
    -0.66
     ſche
    -0.65
    POSITIVE LOGITS
    ArrowToggle
    0.68
     why
    0.68
     how
    0.67
    MessageTagHelper
    0.64
    PerformLayout
    0.59
     testify
    0.58
    #
    0.56
    それだけ
    0.56
    Gambas
    0.55
     testifies
    0.55
    Activations Density 0.289%

    No Known Activations