© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12809
    Prev
    Next
    INDEX
    Explanations

    concepts related to gaming mechanics, particularly around character progression and abilities

    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
    MessageTagHelper
    -0.72
     виправивши
    -0.70
     SwitchCompat
    -0.70
    RenderAtEndOf
    -0.70
     adjournment
    -0.67
     auffi
    -0.67
    abestanden
    -0.65
    SpringRunner
    -0.65
     OMITBAD
    -0.64
    HostException
    -0.63
    POSITIVE LOGITS
     unlock
    0.90
     upgrade
    0.88
     unlocks
    0.85
     unlocked
    0.85
     upgrades
    0.84
     skill
    0.76
     bonus
    0.76
     unlocking
    0.72
    Unlock
    0.71
    unlocked
    0.70
    Activations Density 0.401%

    No Known Activations