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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 2973
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and methods used in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attacc
    -0.45
     designation
    -0.39
     Designation
    -0.38
    ⓧ
    -0.38
     erle
    -0.37
     mounts
    -0.37
    viewDidLoad
    -0.37
    문
    -0.37
     gouver
    -0.37
     explí
    -0.36
    POSITIVE LOGITS
    DeleteBehavior
    0.82
    ]$}
    0.73
     JpaRepository
    0.73
    ContentAsync
    0.71
     tartalomajánló
    0.71
     GenerationType
    0.70
    DataAnnotations
    0.70
    WriteTagHelper
    0.70
    υτό
    0.70
    endphp
    0.68
    Activations Density 1.732%

    No Known Activations