© 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. 6-GEMMASCOPE-RES-16K
    6. 3657
    Prev
    Next
    INDEX
    Explanations

    sentences expressing desires and intentions related to sharing and commenting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imageNamed
    -0.51
    requireNonNull
    -0.50
    wikimedia
    -0.49
     compatible
    -0.49
    PYX
    -0.48
    TargetException
    -0.48
    xmlns
    -0.48
    HostException
    -0.47
     photosynthesis
    -0.47
    compatible
    -0.47
    POSITIVE LOGITS
     виправивши
    0.61
    extAlignment
    0.60
     reminder
    0.58
     disambiguazione
    0.54
     ProtoMessage
    0.53
    odils
    0.51
     remind
    0.50
     warning
    0.50
    Reminder
    0.50
    ༘
    0.49
    Activations Density 0.186%

    No Known Activations