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. 2-GEMMASCOPE-RES-16K
    6. 6184
    Prev
    Next
    INDEX
    Explanations

    code snippets related to image handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IonicModule
    -0.61
    demort
    -0.57
     виправивши
    -0.56
     стаття
    -0.55
     Autorisations
    -0.52
    Zeneca
    -0.52
    wußt
    -0.51
    ########.
    -0.51
    ocyclic
    -0.50
    艋
    -0.49
    POSITIVE LOGITS
     Normdatei
    0.73
    ▾
    0.57
     MERCHANTABILITY
    0.55
     southward
    0.54
     Fue
    0.54
     hObject
    0.53
    CreateIndex
    0.52
    @[+][
    0.51
    utilité
    0.50
    الحياه
    0.50
    Activations Density 0.312%

    No Known Activations