© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1720
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroanxiety and positive emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Transition from negative to positive

    np_acts-logits-general · gemini-2.0-flash

    positive outcomes after comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poorly
    -0.63
    isNaN
    -0.59
    FAILED
    -0.58
    Horrible
    -0.57
    Stderr
    -0.57
     unpopular
    -0.57
     dysfunctional
    -0.56
    Worst
    -0.56
     onError
    -0.54
     плохо
    -0.54
    POSITIVE LOGITS
     positive
    1.35
     Positive
    1.17
    Positive
    1.15
    positive
    1.13
     POSITIVE
    1.11
     favourable
    1.10
     favorable
    1.09
     positif
    1.07
     happy
    1.05
     favourably
    1.04
    Activations Density 1.026%

    No Known Activations