© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'weakness' in various contexts

    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
     conhece
    -0.41
    來說
    -0.41
    나는
    -0.38
     brasileiros
    -0.38
     Ganzen
    -0.38
    ผม
    -0.36
     beliau
    -0.36
     Gegenteil
    -0.36
    นะครับ
    -0.36
     milhares
    -0.36
    POSITIVE LOGITS
    UserScript
    0.76
    onAttach
    0.75
     defaultstate
    0.75
    +#+#
    0.75
     weak
    0.73
    Cyfeiriadau
    0.73
     intptr
    0.72
    dafx
    0.71
     sponsored
    0.70
    onViewCreated
    0.70
    Activations Density 0.309%

    No Known Activations