© 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. 5-GEMMASCOPE-RES-16K
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    code structures that involve mappings or key-value relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ます
    -0.51
     apla
    -0.42
    ri
    -0.41
    s
    -0.41
     valami
    -0.40
     quebra
    -0.40
    de
    -0.40
    卓
    -0.38
     some
    -0.38
    that
    -0.38
    POSITIVE LOGITS
    RectangleBorder
    1.22
    OGND
    1.16
     BoxDecoration
    1.11
    TagHelper
    1.09
     BorderRadius
    1.07
    UIControlState
    1.04
     BoxFit
    1.02
    Revenir
    1.00
    NewUrlParser
    1.00
     كومونز
    1.00
    Activations Density 0.050%

    No Known Activations