© 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. 17-GEMMASCOPE-RES-16K
    6. 1414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or consequence within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nodoc
    -0.53
     gynhyrchwyd
    -0.49
    δό
    -0.49
    stdafx
    -0.48
    inkl
    -0.47
    IMPORTED
    -0.47
    openConnection
    -0.47
    DebuggerNonUser
    -0.47
    TestBed
    -0.47
    tedly
    -0.47
    POSITIVE LOGITS
     eventually
    2.44
    Eventually
    2.37
     Eventually
    2.29
    eventually
    2.21
     eventual
    1.79
     soon
    1.74
     irgendwann
    1.71
     ultimately
    1.64
     uiteindelijk
    1.56
     gradually
    1.51
    Activations Density 0.574%

    No Known Activations