Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6460
    Prev
    Next
    INDEX
    Explanations

    phrasings related to movement or directional verbs

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

    Following "up" or "out"

    np_acts-logits-general · gemini-2.0-flash

    up and out movement

    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
    esistenza
    -0.40
     kezd
    -0.37
    ยัง
    -0.36
     among
    -0.36
     rumbo
    -0.35
     رسد
    -0.35
     başka
    -0.35
     elsewhere
    -0.35
     chegada
    -0.35
    핍
    -0.35
    POSITIVE LOGITS
    DoubleQuotes
    0.58
    TestingModule
    0.57
     esternos
    0.57
    asteroide
    0.57
     ब्रेकडाउन
    0.56
     viewType
    0.56
    principalTable
    0.54
    IntoConstraints
    0.54
    aarrggbb
    0.52
    IBOutlet
    0.50
    Activations Density 0.202%

    No Known Activations