© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 668
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "new" indicating object instantiation in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MutableLiveData
    -0.56
    baseURL
    -0.55
    convertView
    -0.53
    EditText
    -0.50
    textBox
    -0.50
    newItem
    -0.50
    setState
    -0.49
    TextView
    -0.49
    intValue
    -0.49
    fontSize
    -0.48
    POSITIVE LOGITS
    .’”
    0.66
     AppCompatTheme
    0.65
     للمعارف
    0.64
    .'”
    0.64
    ),”
    0.62
    RenderAtEndOf
    0.61
    ).”
    0.61
    帖最后由
    0.60
     الاطلاع
    0.58
    Espèce
    0.57
    Activations Density 0.416%

    No Known Activations