© 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. 13703
    Prev
    Next
    INDEX
    Explanations

    phrases and sentiments related to perseverance and not giving up

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

    Avoidance of giving up

    np_acts-logits-general · gemini-2.0-flash

    never giving up

    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
     Сме
    -0.48
    verwijspagina
    -0.47
    osoba
    -0.46
    zzleHttp
    -0.44
    REM
    -0.44
    牵
    -0.44
     &___
    -0.43
    Сме
    -0.42
    puri
    -0.42
    StrictMode
    -0.42
    POSITIVE LOGITS
     despair
    1.27
     surrender
    1.18
     hopelessness
    1.13
    放弃
    1.11
     quitting
    1.09
     hopeless
    1.09
    放棄
    1.08
     quit
    1.08
    諦
    1.05
     abandoning
    1.04
    Activations Density 0.234%

    No Known Activations