© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12554
    Prev
    Next
    INDEX
    Explanations

    terms related to guidance or direction in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.46
    UniformLocation
    -0.45
     zb
    -0.39
     ProtoMessage
    -0.38
     springfox
    -0.38
    ActionButton
    -0.38
    ägg
    -0.38
     MonoBehaviour
    -0.38
    Clive
    -0.38
     NSCoder
    -0.38
    POSITIVE LOGITS
     guided
    2.11
     Guided
    1.82
    guided
    1.79
    Guided
    1.77
     assisted
    1.77
    assisted
    1.53
     Assisted
    1.53
     mediated
    1.51
    Assisted
    1.46
     supervised
    1.45
    Activations Density 0.353%

    No Known Activations