© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    terms related to parental involvement and communication in educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    ッケージ
    -0.44
    synthe
    -0.42
     مرئيه
    -0.41
    Gambas
    -0.41
     umane
    -0.40
     cref
    -0.40
    outon
    -0.39
    awakeFromNib
    -0.39
     satılık
    -0.38
    ceria
    -0.38
    POSITIVE LOGITS
     parents
    0.98
    Parents
    0.90
     parenting
    0.84
     Parents
    0.82
     parental
    0.81
     Eltern
    0.76
    parents
    0.75
     parent
    0.75
     PARENTS
    0.68
    Parental
    0.68
    Activations Density 0.200%

    No Known Activations