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. 11-GEMMASCOPE-RES-16K
    6. 6910
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical expressions involving the variable "E" and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngilizce
    -0.47
     dép
    -0.47
    افت
    -0.47
    нак
    -0.46
    Avery
    -0.46
    xFFFF
    -0.45
     Fare
    -0.45
    Fare
    -0.44
    bouquet
    -0.44
    tons
    -0.44
    POSITIVE LOGITS
    Datuak
    1.17
    ंदीखरीदारी
    1.12
    AddTagHelper
    0.97
    stdc
    0.92
     محفوظة
    0.82
     MainAxisSize
    0.81
     bezeichneter
    0.81
    tvguidetime
    0.78
     صوتيه
    0.78
    VersionUID
    0.77
    Activations Density 0.260%

    No Known Activations