© 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. 22-GEMMASCOPE-RES-16K
    11. 8161
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional and mental health management

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

    negative feelings/self-sabotage

    np_acts-logits-general · gemini-2.0-flash

    self-sabotage and struggle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestingModule
    -0.68
    ﾟ)
    -0.66
    Hentet
    -0.60
    ölker
    -0.60
    writerow
    -0.59
    fhir
    -0.58
     estekak
    -0.57
    entuan
    -0.56
    Kjelder
    -0.55
    łbym
    -0.55
    POSITIVE LOGITS
     negative
    0.84
     self
    0.77
     unhealthy
    0.76
     perfection
    0.73
     Negative
    0.71
     sabo
    0.71
     negativity
    0.70
     insecure
    0.67
     blaming
    0.66
     insecurity
    0.66
    Activations Density 0.379%

    No Known Activations