© 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. 9-GEMMASCOPE-RES-16K
    6. 9054
    Prev
    Next
    INDEX
    Explanations

    technical terms related to applications, particularly in the context of grading and scoring systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.48
    aysia
    -0.45
    曖昧さ回避
    -0.44
    nolia
    -0.43
    +}
    -0.42
    atguigu
    -0.42
    ouche
    -0.41
    デー
    -0.41
    onChanged
    -0.40
    lateinit
    -0.40
    POSITIVE LOGITS
     weighting
    0.78
    Portály
    0.71
     puntuación
    0.68
     MediatR
    0.66
    Kanpo
    0.64
    Bewertung
    0.63
    BorderLayout
    0.62
     scoring
    0.62
     ModelExpression
    0.62
     aveug
    0.61
    Activations Density 0.385%

    No Known Activations