Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8946
    Prev
    Next
    INDEX
    Explanations

    key phrases regarding priorities and values in various contexts

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

    Word after "the"

    np_acts-logits-general · gemini-2.0-flash

    core aspects and qualities

    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
    المناصب
    -0.50
    ativement
    -0.43
    scrollY
    -0.42
    carpus
    -0.40
    DataSetChanged
    -0.39
    TargetApi
    -0.39
     nigra
    -0.39
    pageY
    -0.39
    ╝
    -0.39
    jsp
    -0.39
    POSITIVE LOGITS
    InputBorder
    0.83
     thing
    0.63
     AssemblyVersion
    0.63
    NUMX
    0.63
     paramount
    0.60
    fecture
    0.57
     विश्वसनीयता
    0.57
     dominante
    0.57
     attribute
    0.57
    palabra
    0.56
    Activations Density 0.263%

    No Known Activations