© 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. 13115
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "reserved" related to copyright or licensing information

    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
    DebuggerNonUser
    -0.82
     MonoBehaviour
    -0.82
     --;
    -0.74
     Hover
    -0.71
    PreferredItem
    -0.70
    hela
    -0.70
     Gloves
    -0.70
     Sver
    -0.67
    Geographie
    -0.67
    UseVisualStyle
    -0.67
    POSITIVE LOGITS
     reserved
    1.26
    axios
    1.14
     Reserved
    1.06
    Reserved
    1.03
    reserved
    0.96
     axios
    0.93
     RESERVED
    0.88
     مشين
    0.80
     reservados
    0.74
     reservado
    0.68
    Activations Density 0.010%

    No Known Activations