Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8621
    Prev
    Next
    INDEX
    Explanations

    common determiners and articles in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    :✨
    -0.90
     the
    -0.75
    Tikang
    -0.71
     nakalista
    -0.66
    Merkmale
    -0.66
     OMITBAD
    -0.66
    Personendaten
    -0.66
    SourceChecksum
    -0.66
    httphttps
    -0.66
    تقاوى
    -0.66
    POSITIVE LOGITS
    . 
    0.24
    !
    0.24
    .
    0.23
    EDEFAULT
    0.22
    latego
    0.22
     peuples
    0.21
    ്‍
    0.21
    FT
    0.21
    Ỏ
    0.21
    !
    0.20
    Activations Density 3.760%

    No Known Activations