© 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. 25-GEMMASCOPE-RES-16K
    6. 8993
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of understanding or absence of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.88
    حوالہ
    -0.70
    sizeCache
    -0.68
    PhysRevLett
    -0.66
     linkovi
    -0.62
    Fantastic
    -0.60
     transfieras
    -0.59
     Gorgeous
    -0.58
     Roskov
    -0.57
     nakalista
    -0.56
    POSITIVE LOGITS
     clear
    1.23
     reliable
    1.18
     accurate
    1.17
     unambiguous
    1.13
     precise
    1.02
     clearly
    1.01
     adequate
    0.97
     sufficiently
    0.95
     well
    0.93
     sound
    0.93
    Activations Density 1.259%

    No Known Activations