© 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. 20-GEMMASCOPE-RES-16K
    11. 6882
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and bounds related to convergence

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

    Expressions involving absolute values and norms

    np_acts-logits-general · gemini-2.0-flash

    absolute value and norms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.56
    סף
    -0.53
    RenderAtEndOf
    -0.52
    ]")]
    -0.51
    */),
    -0.49
    parken
    -0.46
    principalTable
    -0.46
    PostConstruct
    -0.45
    --
    -0.45
    --}}
    -0.44
    POSITIVE LOGITS
    abs
    1.40
     $|
    1.35
     absolute
    1.35
    =|
    1.28
     $|\
    1.25
     abs
    1.25
    Abs
    1.24
    |
    1.24
    $|
    1.23
    absolute
    1.21
    Activations Density 1.580%

    No Known Activations