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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15120
    Prev
    Next
    INDEX
    Explanations

    information pertaining to monitoring systems and assistance from manufacturers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedName
    -0.58
    writerow
    -0.49
     capelli
    -0.48
     cheveux
    -0.47
    ?
    -0.46
     fraî
    -0.46
     o
    -0.46
     normes
    -0.45
     communs
    -0.44
     cumplimiento
    -0.44
    POSITIVE LOGITS
     <=",
    0.81
    DebuggerNonUser
    0.80
     للاسماء
    0.78
     AssemblyProduct
    0.78
     שוליים
    0.74
    ftagPool
    0.74
    省市镇
    0.73
     doubtnut
    0.72
    NewUrlParser
    0.71
    mybatisplus
    0.71
    Activations Density 0.079%

    No Known Activations