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. 24-GEMMASCOPE-RES-16K
    6. 12835
    Prev
    Next
    INDEX
    Explanations

    code snippets or structured data related to programming or APIs

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

    Code, foreign language, or unusual syntax

    np_acts-logits-general · gemini-2.0-flash

    Tak, Finland, brought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyleAttr
    -0.70
    +#+#
    -0.64
    ConverterFactory
    -0.61
    providedIn
    -0.59
     FetchType
    -0.58
    astify
    -0.58
    GrantedAuthority
    -0.57
    WriteTagHelper
    -0.57
    GraphicsUnit
    -0.57
    TagMode
    -0.57
    POSITIVE LOGITS
     فريبيس
    0.63
    žin
    0.48
    RegressionTest
    0.46
     bericht
    0.45
    atric
    0.43
    acteria
    0.43
    __":
    
    0.43
    ädie
    0.42
     crow
    0.42
    arine
    0.42
    Activations Density 0.170%

    No Known Activations