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. 16-GEMMASCOPE-RES-16K
    6. 1325
    Prev
    Next
    INDEX
    Explanations

    terms related to definitions and differentiation

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

    definitions or derivations

    np_acts-logits-general · gemini-2.0-flash

    definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.81
    __':
    
    -0.68
     AssemblyVersion
    -0.58
    StructEnd
    -0.58
    AndroidJUnit
    -0.58
    apunov
    -0.55
    ContentAsync
    -0.54
    Support
    -0.53
     Support
    -0.53
    istoitu
    -0.52
    POSITIVE LOGITS
     definition
    0.74
     déf
    0.67
     definição
    0.66
     Defin
    0.63
     définition
    0.63
     define
    0.63
     depolar
    0.63
     def
    0.62
     Déf
    0.62
     defining
    0.62
    Activations Density 0.185%

    No Known Activations