Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 359
    Prev
    Next
    INDEX
    Explanations

    queries expressing confusion or uncertainty in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.69
    HostException
    -0.61
     Jefus
    -0.59
    ⤹
    -0.58
     purpoſe
    -0.58
    новниш
    -0.57
     pleaſure
    -0.56
     SwitchCompat
    -0.55
     myſelf
    -0.55
    XmlAccessorType
    -0.54
    POSITIVE LOGITS
     need
    0.39
     needs
    0.37
     Numerade
    0.34
     worries
    0.34
     lost
    0.34
     Need
    0.34
     insufficient
    0.34
     sprinkle
    0.33
    Need
    0.33
    र्भ
    0.33
    Activations Density 0.581%

    No Known Activations