© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35232
    Prev
    Next
    INDEX
    Explanations

    references to anxiety and related emotional states

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

    anxiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}}
    -0.40
    █
    -0.37
    }}},
    -0.36
    pagestyle
    -0.36
    "}")
    -0.36
    <0xE1>
    -0.35
    })(
    -0.35
     обо
    -0.35
    }))
    -0.35
    }}.
    -0.35
    POSITIVE LOGITS
    Anxiety
    1.21
     Anxiety
    1.18
    anxiety
    1.16
     anxiety
    1.09
    xiety
    0.99
     anxieties
    0.98
     ansiedad
    0.96
     anxious
    0.90
     ansiedade
    0.85
     anxiously
    0.76
    Activations Density 0.006%

    No Known Activations