© 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. 916
    Prev
    Next
    INDEX
    Explanations

    technical code-related terms and commands associated with software configurations and installations

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

    "x64" or "amd" mentions

    np_acts-logits-general · gemini-2.0-flash

    x86, x64, amd64

    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
     important
    -0.66
     matters
    -0.59
     pressing
    -0.57
     wichtig
    -0.57
     priority
    -0.57
     Important
    -0.56
     other
    -0.55
    oredCriteria
    -0.54
     priorities
    -0.54
    ftagPool
    -0.53
    POSITIVE LOGITS
    amd
    0.66
     arquitectura
    0.61
    LayoutStyle
    0.56
    PRNewswire
    0.56
    tifact
    0.54
     éner
    0.53
     ivelany
    0.53
    PostMapping
    0.53
    PreferredItem
    0.52
     arquitetura
    0.52
    Activations Density 0.347%

    No Known Activations