© 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. 0-GEMMASCOPE-RES-16K
    6. 9934
    Prev
    Next
    INDEX
    Explanations

    the concept of being correct or accurate, especially in the context of rights and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölker
    -0.49
    amarca
    -0.41
     AppCompatTheme
    -0.40
    AnimationsModule
    -0.39
    arpa
    -0.38
    (;;)
    -0.38
    zaar
    -0.38
    ⓧ
    -0.37
    orianCalendar
    -0.37
    发表于
    -0.36
    POSITIVE LOGITS
     right
    3.98
     Right
    3.58
    Right
    3.56
     RIGHT
    3.45
    right
    3.44
    RIGHT
    3.17
    右
    2.38
     derecho
    2.30
     righ
    2.25
     derecha
    2.22
    Activations Density 0.135%

    No Known Activations