© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    supportive interactions and efforts to help others, particularly in the context of social and emotional guidance

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

    following "others" or "students"

    np_acts-logits-general · gemini-2.0-flash

    beginners or young people

    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
     intptr
    -0.41
    انجليز
    -0.38
    你觉得
    -0.35
    يميديا
    -0.35
    LabelTagHelper
    -0.35
     excesses
    -0.35
    Erreferentziak
    -0.34
     whoſe
    -0.34
    SharedDtor
    -0.33
     consultato
    -0.32
    POSITIVE LOGITS
    fjspx
    0.48
     rookies
    0.47
     beginners
    0.46
     initComponents
    0.45
     newbies
    0.44
     novices
    0.44
     Rookie
    0.42
     youngsters
    0.42
    autique
    0.42
     disciples
    0.41
    Activations Density 0.209%

    No Known Activations