© 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. 7-GEMMASCOPE-RES-16K
    6. 15997
    Prev
    Next
    INDEX
    Explanations

    quantities of hours worked or spent in various contexts, especially related to service or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaces
    -0.40
    siapkan
    -0.38
    sweise
    -0.34
     Hancock
    -0.34
     pazi
    -0.34
    ReusableCell
    -0.33
    edenken
    -0.33
    faßt
    -0.32
     Jungen
    -0.32
     hairy
    -0.32
    POSITIVE LOGITS
     hours
    2.53
     Hours
    2.48
    Hours
    2.36
     Hour
    2.28
    hours
    2.27
     hour
    2.27
    Hour
    2.20
     HOURS
    2.16
    hour
    2.13
     HOUR
    2.05
    Activations Density 0.122%

    No Known Activations