© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8704
    Prev
    Next
    INDEX
    Explanations

    language and constructs related to conditional capabilities or potential outcomes

    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
     itſelf
    -0.88
     ſeveral
    -0.83
     Cæsar
    -0.74
     againſt
    -0.74
     poffible
    -0.74
     pleaſure
    -0.74
    ſelf
    -0.72
     leſs
    -0.72
     houſe
    -0.72
     himſelf
    -0.71
    POSITIVE LOGITS
     Dabei
    0.68
     Schließlich
    0.65
    Dabei
    0.63
     mit
    0.61
    PyExc
    0.59
     bis
    0.59
    ندما
    0.58
    taus
    0.58
    CORBA
    0.56
     Vielleicht
    0.55
    Activations Density 0.061%

    No Known Activations