© 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. 1-GEMMASCOPE-RES-16K
    6. 2459
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific names or terms associated with legal or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stateProvider
    -0.56
    TargetException
    -0.55
     protoimpl
    -0.52
    TagMode
    -0.51
    Javadoc
    -0.50
    abstractmethod
    -0.50
    mybatisplus
    -0.50
     Normdatei
    -0.50
     initComponents
    -0.50
    fromnode
    -0.49
    POSITIVE LOGITS
    Tal
    0.76
     tal
    0.72
     Tal
    0.70
     blo
    0.68
     Blo
    0.61
     stretching
    0.61
    Blo
    0.60
     TAL
    0.59
    blo
    0.56
     stretch
    0.52
    Activations Density 0.396%

    No Known Activations