© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14730
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle movement and traffic management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    directional movement and rotational motion descriptions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    허
    -0.40
    mitives
    -0.39
    IUrlHelper
    -0.37
    VYMaps
    -0.37
     &___
    -0.36
     prek
    -0.36
     OFDb
    -0.35
     juggling
    -0.35
    sidemargin
    -0.34
    ########.
    -0.34
    POSITIVE LOGITS
     upward
    1.46
     outward
    1.42
     downward
    1.42
     outwards
    1.40
     downwards
    1.38
     inward
    1.26
     upwards
    1.23
     outgoing
    1.21
     forward
    1.20
     outbound
    1.19
    Activations Density 0.884%

    No Known Activations