© 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. 0-GEMMASCOPE-RES-16K
    6. 9011
    Prev
    Next
    INDEX
    Explanations

    references to the term "Basic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.66
     ControllerBase
    -0.66
    stdarg
    -0.61
    RetentionPolicy
    -0.61
     PropertyChanged
    -0.61
     iload
    -0.60
     pylint
    -0.58
    ğum
    -0.58
    AxisAlignment
    -0.58
    Hochspringen
    -0.57
    POSITIVE LOGITS
     Project
    0.67
     –
    0.64
     Ru
    0.64
    "…
    0.64
    …
    0.63
     …
    0.63
    …).
    0.60
    …"
    0.55
    ”…
    0.54
     …)
    0.53
    Activations Density 0.173%

    No Known Activations