© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5857
    Prev
    Next
    INDEX
    Explanations

    terms indicating additional information or contrast

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

    Follows "more", "against", "sure", or "besides"

    np_acts-logits-general · gemini-2.0-flash

    what is more

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ológico
    -0.41
     olmayan
    -0.38
     kapan
    -0.38
    (!__
    -0.37
    blå
    -0.36
    ológicos
    -0.35
    ljiv
    -0.35
     boste
    -0.35
     temprana
    -0.34
    ledem
    -0.34
    POSITIVE LOGITS
     noDo
    0.64
    __":
    
    0.59
    ECONDS
    0.59
     ſte
    0.57
     ſche
    0.55
    stateProvider
    0.55
     ſch
    0.55
    MockBean
    0.53
     ſta
    0.53
     eſt
    0.52
    Activations Density 1.516%

    No Known Activations