© 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. 119666
    Prev
    Next
    INDEX
    Explanations

    references to attributes or characteristics related to materials and processes

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

    finalizing/characterization/fabricating

    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
     Audiodateien
    -0.59
    WRP
    -0.55
    AddTagHelper
    -0.53
    rollo
    -0.52
    <bos>
    -0.52
    Wired
    -0.49
     joão
    -0.48
    biology
    -0.48
     Yank
    -0.48
    liament
    -0.48
    POSITIVE LOGITS
    хьтан
    0.42
    MessageOf
    0.41
     informée
    0.37
    SpringRunner
    0.34
    AnimationsModule
    0.34
    Spenden
    0.34
    gbaar
    0.33
     venuto
    0.33
     real
    0.32
     appena
    0.31
    Activations Density 0.180%

    No Known Activations