© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    terms related to tightness and securing mechanisms in various contexts

    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
     ujednoznacz
    -0.58
    Mə
    -0.56
     Normdatei
    -0.56
    Portale
    -0.56
    GOTREF
    -0.54
    Kanpo
    -0.52
    cua
    -0.52
     dilution
    -0.51
    !*\
    -0.50
    gjenge
    -0.50
    POSITIVE LOGITS
     tight
    1.71
     tightly
    1.62
     Tight
    1.51
     tighter
    1.51
    tight
    1.44
    Tight
    1.43
     closed
    1.43
     tighten
    1.27
     tightened
    1.26
     shut
    1.25
    Activations Density 0.623%

    No Known Activations