Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16367
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their effects, particularly those related to neurobiology and mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused43>
    -0.84
    <pad>
    -0.84
    <unused41>
    -0.84
    <unused51>
    -0.84
    <unused23>
    -0.83
    <unused3>
    -0.83
    <unused20>
    -0.83
    <unused42>
    -0.83
    <unused17>
    -0.83
    [@BOS@]
    -0.83
    POSITIVE LOGITS
    ējās
    0.40
    ########.
    0.38
    [-]
    0.32
     وتسجيلات
    0.30
    ________
    0.28
     inſ
    0.27
     través
    0.27
     dė
    0.27
     francés
    0.27
     ModelExpression
    0.27
    Activations Density 2.498%

    No Known Activations