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. 20-GEMMASCOPE-RES-16K
    6. 11758
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and regions within a context

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

    Cities or locations

    np_acts-logits-general · gemini-2.0-flash

    downtown Greeneville

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplayer
    -0.69
    ValueStyle
    -0.66
     Ferri
    -0.61
    DeleteBehavior
    -0.60
    Portale
    -0.60
    Composable
    -0.55
    enderror
    -0.55
     Sor
    -0.54
    ROIT
    -0.54
     disambiguazione
    -0.53
    POSITIVE LOGITS
    UnsafeEnabled
    0.73
     CreateTagHelper
    0.69
     Springs
    0.64
     Springfield
    0.55
     Bloomington
    0.53
     Oyo
    0.53
     Abp
    0.52
     gynhyrchwyd
    0.52
     Grenoble
    0.51
    Bloom
    0.50
    Activations Density 0.265%

    No Known Activations