© 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. 18-GEMMASCOPE-RES-16K
    6. 3576
    Prev
    Next
    INDEX
    Explanations

    terms related to fiscal and calendar years

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

    a point in time

    np_acts-logits-general · gemini-2.0-flash

    time periods and their relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eventually
    -0.43
     Lof
    -0.42
    bod
    -0.41
     IBOutlet
    -0.41
     Delf
    -0.41
    PDOException
    -0.40
     itſelf
    -0.40
    ége
    -0.40
    zp
    -0.40
     matched
    -0.40
    POSITIVE LOGITS
     preceding
    1.05
     past
    1.02
     écoulé
    1.01
     upcoming
    1.01
     previous
    1.00
     виправивши
    0.98
    upcoming
    0.97
    previous
    0.96
    تقاوى
    0.93
    past
    0.91
    Activations Density 0.156%

    No Known Activations