© 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. 16-GEMMASCOPE-RES-16K
    6. 1116
    Prev
    Next
    INDEX
    Explanations

    references to administrative processes and organizational structures

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

    containment or being "inside"

    np_acts-logits-general · gemini-2.0-flash

    part of within integrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.85
     مشين
    -0.78
    HostException
    -0.72
     CreateTagHelper
    -0.68
    ValueGeneration
    -0.67
    LookAnd
    -0.66
     <>",
    -0.64
     Chwiliwch
    -0.63
    NUMX
    -0.62
    StoryboardSegue
    -0.61
    POSITIVE LOGITS
     inside
    0.89
     within
    0.84
     embedded
    0.80
     attached
    0.80
     dentro
    0.78
     innerhalb
    0.76
     Dentro
    0.76
    within
    0.73
     WITHIN
    0.73
    inside
    0.73
    Activations Density 0.630%

    No Known Activations