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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3027
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or contractual arrangements on a recurring basis

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

    "... basis" or "... BASIS"

    np_acts-logits-general · gemini-2.0-flash

    on a basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.76
    
    -0.67
     lenker
    -0.64
    +#+
    -0.64
     TextAppearance
    -0.64
     насељу
    -0.62
    MENAFN
    -0.62
    TargetException
    -0.61
     Vikipedi
    -0.60
    __":
    -0.59
    POSITIVE LOGITS
     basis
    2.03
     Basis
    1.59
    basis
    1.59
    Basis
    1.49
     BASIS
    1.44
     bases
    1.35
    bases
    1.04
    Bases
    1.01
     Bases
    1.01
     Grundlage
    1.00
    Activations Density 0.140%

    No Known Activations