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. 4714
    Prev
    Next
    INDEX
    Explanations

    chemical symbols and notations related to molecular structures and interactions

    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
     tangki
    -0.40
     bete
    -0.39
     sơ
    -0.37
     πρά
    -0.37
     Gobierno
    -0.35
    gantung
    -0.34
     bekommen
    -0.34
    ide
    -0.33
     préféré
    -0.33
     která
    -0.33
    POSITIVE LOGITS
    +#+#
    1.30
    ThroughAttribute
    1.26
     utafitiHapana
    1.23
     ComVisible
    1.22
    GEBURTSDATUM
    1.19
    Geplaatst
    1.16
    StructEnd
    1.13
    SourceChecksum
    1.10
    ftagPool
    1.09
    ScopeManager
    1.05
    Activations Density 0.902%

    No Known Activations