© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    terms related to auditory devices and conditions

    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
    IntoConstraints
    -0.35
     ease
    -0.34
     plas
    -0.34
    amssymb
    -0.34
    SupportActionBar
    -0.33
    XmlRootElement
    -0.33
     ویکی‌پدی
    -0.32
    ()?;
    -0.32
     ""));
    -0.31
    +:+
    -0.31
    POSITIVE LOGITS
     Hearing
    1.11
     hearing
    1.08
    Hearing
    1.07
     oreille
    1.00
     ears
    1.00
     ear
    0.98
     deafness
    0.97
     HEARING
    0.94
    hearing
    0.93
     Ears
    0.89
    Activations Density 0.320%

    No Known Activations