© 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. 382
    Prev
    Next
    INDEX
    Explanations

    phrases related to outcomes and finality

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

    conclusions or outcomes

    np_acts-logits-general · gemini-2.0-flash

    conclusion or outcome

    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
    twimg
    -0.79
     >=",
    -0.79
     EconPapers
    -0.76
    TestingModule
    -0.72
    ">//
    -0.71
     ExecuteAsync
    -0.70
    ThroughAttribute
    -0.69
    PerformLayout
    -0.67
    OGND
    -0.67
    WithIOException
    -0.66
    POSITIVE LOGITS
     ultimately
    1.84
     Ultimately
    1.75
    Ultimately
    1.70
     uiteindelijk
    1.67
     eventually
    1.58
     end
    1.47
     finalement
    1.37
    Eventually
    1.37
     Eventually
    1.35
    eventually
    1.34
    Activations Density 0.184%

    No Known Activations