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. 19-GEMMASCOPE-RES-16K
    6. 2069
    Prev
    Next
    INDEX
    Explanations

    HTML header tags and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AllAfrica
    -0.79
     AssemblyCulture
    -0.73
    олові
    -0.64
     FetchType
    -0.64
     للمعارف
    -0.64
    makeText
    -0.63
    LLocation
    -0.61
     ExecuteAsync
    -0.61
    NUMX
    -0.59
     MessageBoxIcon
    -0.59
    POSITIVE LOGITS
    OGND
    0.78
    <eos>
    0.67
     CreateTagHelper
    0.61
    BeginContext
    0.59
    })));
    0.58
    ↵↵↵↵↵
    0.57
    ↵↵↵↵↵↵↵↵
    0.53
    <h2>
    0.53
     murmured
    0.52
    ↵↵
    0.52
    Activations Density 0.073%

    No Known Activations