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. 0-GEMMASCOPE-RES-16K
    6. 8611
    Prev
    Next
    INDEX
    Explanations

    the term "spin" and its variations in various contexts, indicating a focus on spinning or rotational concepts

    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
     obligatory
    -0.52
     her
    -0.46
     du
    -0.45
     Lese
    -0.44
     oblig
    -0.44
    ér
    -0.43
     de
    -0.42
     contact
    -0.41
     pri
    -0.41
     (
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.77
    richTextPanel
    0.75
    MemoryWarning
    0.69
     spins
    0.66
     للاسماء
    0.66
     spinners
    0.65
    RegressionTest
    0.63
    spin
    0.63
    SerializedSize
    0.62
    RTDA
    0.62
    Activations Density 0.211%

    No Known Activations