© 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. 10-GEMMASCOPE-RES-16K
    11. 1991
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     form
    -0.46
     drive
    -0.45
     #
    -0.44
     turn
    -0.43
     darb
    -0.42
     success
    -0.42
    -
    -0.41
     get
    -0.41
     un
    -0.41
     go
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    1.14
     beginnetje
    1.10
    MessageTagHelper
    0.99
    hdashline
    0.91
    ISupport
    0.91
     Meksiku
    0.90
    AutoScaleMode
    0.89
    󠁴
    0.86
    OrNil
    0.85
     Signalez
    0.84
    Activations Density 0.278%

    No Known Activations