© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 487
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "time" along with phrases that indicate timing and action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences and phrases related to time and deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocino
    -0.57
     препратки
    -0.56
    verwijspagina
    -0.55
    ficulty
    -0.53
    XmlAccessType
    -0.53
    </caption>
    -0.52
    ctif
    -0.52
    */),
    -0.52
    jenner
    -0.52
    ']],
    -0.51
    POSITIVE LOGITS
     ready
    0.71
    そろそろ
    0.68
     Ready
    0.67
    Ready
    0.65
     urgente
    0.64
     time
    0.63
    READY
    0.62
    ripe
    0.62
     stage
    0.62
    stage
    0.62
    Activations Density 0.080%

    No Known Activations