© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or arrival

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

    followed by "to" or "up"

    np_acts-logits-general · gemini-2.0-flash

    comes to, came up, come together

    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
     jScrollPane
    -0.60
     }}-
    -0.52
    DllImport
    -0.52
    RetentionPolicy
    -0.49
    ритори
    -0.49
     addSubview
    -0.48
    )))),
    -0.46
    ∛
    -0.45
     للمعارف
    -0.45
    மை
    -0.45
    POSITIVE LOGITS
    MLLoader
    0.62
    principalColumn
    0.60
    fjspx
    0.59
    Décès
    0.59
     Vikipedi
    0.58
     createSlice
    0.58
    DrawerToggle
    0.58
    Datuak
    0.57
     NavController
    0.56
    StructEnd
    0.56
    Activations Density 0.103%

    No Known Activations