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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8653
    Prev
    Next
    INDEX
    Explanations

    the concept of 'world' and its variations or 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
    parsedMessage
    -0.50
    IsMutable
    -0.50
    IntoConstraints
    -0.47
     مرئيه
    -0.46
     Efq
    -0.46
     للاسماء
    -0.45
    RTCK
    -0.44
    MessageTagHelper
    -0.42
    withIdentifier
    -0.40
    PostInfinity
    -0.40
    POSITIVE LOGITS
     world
    3.13
    world
    3.09
    World
    2.97
     World
    2.89
    WORLD
    2.70
     WORLD
    2.69
     worlds
    2.41
     mundo
    2.25
    世界
    2.16
    worlds
    2.16
    Activations Density 0.163%

    No Known Activations