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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81272
    Prev
    Next
    INDEX
    Explanations

    terms related to marine life, especially sharks and their habitats

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

    shark trip

    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
     yyr
    -0.41
     Hote
    -0.39
     testify
    -0.35
     hosp
    -0.35
     Hot
    -0.34
     hote
    -0.34
     surla
    -0.33
    yz
    -0.33
    Descriptor
    -0.31
     Hoc
    -0.31
    POSITIVE LOGITS
     mijne
    0.63
    ActionCreators
    0.58
    EDEFAULT
    0.55
     كورة
    0.54
     ContentValues
    0.51
    UserScript
    0.50
     CreateTagHelper
    0.48
     schoenen
    0.48
     poveznice
    0.46
     AssemblyVersion
    0.45
    Activations Density 0.073%

    No Known Activations