© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8280
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to low and losses, particularly in the context of healthcare or medical conditions

    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
     CURIAM
    -0.60
     ब्रेकडाउन
    -0.57
    хьтан
    -0.50
    TargetApi
    -0.45
    httphttps
    -0.43
    /**
    -0.43
    ApiProperty
    -0.42
     CanadaChoose
    -0.40
    tagPool
    -0.40
    ActionCreators
    -0.38
    POSITIVE LOGITS
     lo
    1.71
    Lo
    1.71
    LO
    1.69
    lo
    1.66
     LO
    1.65
     Lo
    1.63
     Lob
    1.42
    lob
    1.41
     ло
    1.41
     lobe
    1.39
    Activations Density 0.508%

    No Known Activations