© 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. 3-GEMMASCOPE-RES-16K
    6. 1996
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding, grasping, and maintaining control or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Requirement
    -0.50
    Aktualisiert
    -0.45
    intra
    -0.43
    ॰
    -0.42
    程
    -0.42
    Stam
    -0.41
    WindowEvent
    -0.41
    ษัท
    -0.41
     requirement
    -0.40
    mapsto
    -0.39
    POSITIVE LOGITS
     grip
    1.29
     grips
    1.16
     grasp
    1.15
     Grip
    1.12
    DebuggerNonUser
    1.09
    grip
    1.06
     grasping
    1.06
     grasped
    1.04
    Grip
    1.04
     grabs
    1.01
    Activations Density 0.366%

    No Known Activations