© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13855
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines and decision-making processes in public health and community involvement

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

    Lists of people or groups

    np_acts-logits-general · gemini-2.0-flash

    stakeholders, clients, users, collectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    variation
    -0.30
    text
    -0.27
     volume
    -0.27
    regler
    -0.27
     ten
    -0.26
    CHARACTER
    -0.25
     怎样
    -0.25
     dep
    -0.25
     variation
    -0.25
     text
    -0.25
    POSITIVE LOGITS
    protoimpl
    0.90
    AddTagHelper
    0.81
    Personensuche
    0.74
    tagHelperRunner
    0.69
     EconPapers
    0.69
    NameInMap
    0.68
    IsPostBack
    0.65
    QMetaType
    0.64
    expandindo
    0.64
    OGND
    0.64
    Activations Density 0.184%

    No Known Activations