© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8793
    Prev
    Next
    INDEX
    Explanations

    the use of quotation marks, particularly in relation to phrases and dialogue

    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
     ſhall
    -0.46
     déchir
    -0.43
     "{{
    -0.43
     strictement
    -0.41
     Vascular
    -0.41
    岿
    -0.41
    󠁢
    -0.41
     Houſe
    -0.41
     fevere
    -0.40
     Vay
    -0.40
    POSITIVE LOGITS
    ”
    0.67
    enterOuterAlt
    0.57
     <>",
    0.51
    WebElementEntity
    0.49
     Италијани
    0.46
    </em>
    0.45
    !!”
    0.44
    ?”
    0.44
    ...”
    0.44
    yntaxException
    0.44
    Activations Density 0.095%

    No Known Activations