© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10843
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to loss and missing something

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

    "lost"

    np_acts-logits-general · gemini-2.0-flash

    loss of capacity, interest, or consciousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.80
     ProtoMessage
    -0.75
     surla
    -0.69
    RectangleBorder
    -0.66
    цездатний
    -0.66
     AssemblyTitle
    -0.65
     Normdatei
    -0.64
     ब्रेकडाउन
    -0.64
    extAlignment
    -0.64
    ⟬
    -0.64
    POSITIVE LOGITS
     loss
    1.59
     lost
    1.58
    Lost
    1.56
     lose
    1.52
     Lost
    1.51
    Loss
    1.45
     Loss
    1.44
     losing
    1.42
    lost
    1.42
     loses
    1.38
    Activations Density 0.112%

    No Known Activations