© 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. 21-GEMMASCOPE-RES-16K
    6. 12767
    Prev
    Next
    INDEX
    Explanations

    negations related to abilities or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.71
    UserScript
    -0.53
    Trayectoria
    -0.49
     intptr
    -0.48
    GraphicsUnit
    -0.46
    ChrTalk
    -0.45
    tonode
    -0.44
     mobili
    -0.44
    tender
    -0.44
     Vergnügen
    -0.44
    POSITIVE LOGITS
     imagine
    0.66
     tell
    0.58
     vedo
    0.56
     wait
    0.56
    IUrlHelper
    0.55
     speak
    0.54
    seille
    0.53
    Believe
    0.53
    EnumValue
    0.53
     WAIT
    0.53
    Activations Density 0.068%

    No Known Activations