© 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. 3-GEMMASCOPE-RES-16K
    6. 6465
    Prev
    Next
    INDEX
    Explanations

    references to inspection and therapy processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deposit
    -0.45
     deposition
    -0.43
     induce
    -0.43
     DEPOS
    -0.43
     dépos
    -0.42
    生
    -0.42
    Slf
    -0.41
    Deposit
    -0.40
    .*")]
    -0.40
     生
    -0.40
    POSITIVE LOGITS
     prescription
    0.95
     Prescription
    0.88
    prescription
    0.86
     prescriptions
    0.85
     prescribed
    0.81
    Prescription
    0.79
     arbitration
    0.77
    pres
    0.74
     prescribe
    0.73
     prescribes
    0.72
    Activations Density 0.115%

    No Known Activations