© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 191
    Prev
    Next
    INDEX
    Explanations

    terms related to rafting and related activities

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

    refractory epilepsy, raft, RTS pin

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Corne
    -0.46
     Macaulay
    -0.45
     Magenta
    -0.45
     Cc
    -0.44
    Federico
    -0.43
     Jennie
    -0.43
    Debbie
    -0.41
     Coder
    -0.41
    Tikang
    -0.41
    BROWN
    -0.41
    POSITIVE LOGITS
     raft
    1.93
     Raft
    1.85
     rafts
    1.72
     rafting
    1.60
    raft
    1.60
    RAFT
    1.04
     Raf
    1.02
    筏
    1.01
    Raf
    0.99
    rafts
    0.98
    Activations Density 0.001%

    No Known Activations