© 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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7750
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and bioinformatics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.74
     للمعارف
    -0.61
     kasarigan
    -0.52
    出版年
    -0.51
     externi
    -0.50
    RegressionTest
    -0.50
    ModelForm
    -0.49
     незавершена
    -0.48
    المشاركات
    -0.48
     Ds
    -0.48
    POSITIVE LOGITS
     ""],
    0.40
     GenerationType
    0.40
    ("-");
    0.38
    vikling
    0.38
     jsonArray
    0.36
     zwey
    0.36
     Vergnügen
    0.36
    glise
    0.36
     zelve
    0.36
    (""));
    0.35
    Activations Density 2.043%

    No Known Activations