© 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. 33-GEMMASCOPE-RES-16K
    6. 533
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to measurements and definitions in scientific or engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.48
    rungsseite
    -0.48
     Administrativna
    -0.43
     للاسماء
    -0.40
     ProtoMessage
    -0.40
    haikusbot
    -0.39
     SwitchCompat
    -0.38
    లాలు
    -0.38
    endphp
    -0.38
     Temporary
    -0.38
    POSITIVE LOGITS
     falling
    1.55
     fall
    1.42
     drop
    1.37
     Falling
    1.35
     falls
    1.35
    Falling
    1.32
    falling
    1.30
     dropping
    1.27
    fall
    1.25
     FALL
    1.25
    Activations Density 0.272%

    No Known Activations