© 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. 20-GEMMASCOPE-RES-16K
    6. 6089
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or requirement

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

    "need" followed by "for" or a form of "exist"

    np_acts-logits-general · gemini-2.0-flash

    need for or exists

    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
    ViewFeatures
    -0.74
    colhead
    -0.70
    principalColumn
    -0.68
    ]};
    -0.62
    󠁢
    -0.60
    $}}
    -0.59
    MemoryWarning
    -0.59
    tonsoft
    -0.59
     DbSet
    -0.59
    GATE
    -0.58
    POSITIVE LOGITS
     fulfilled
    0.65
    Ful
    0.64
    lessness
    0.62
     rencontr
    0.62
     fulfillment
    0.59
     arises
    0.59
    iness
    0.58
     fulfilment
    0.57
     couverts
    0.57
     mendes
    0.57
    Activations Density 0.136%

    No Known Activations