© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15878
    Prev
    Next
    INDEX
    Explanations

    expressions related to progress and movement forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Front
    -0.28
     der
    -0.28
     Glanz
    -0.27
    ranos
    -0.26
    medriver
    -0.26
    couvrir
    -0.26
    جانب
    -0.26
     background
    -0.26
    background
    -0.25
     Background
    -0.25
    POSITIVE LOGITS
     forward
    3.58
    forward
    3.06
     Forward
    3.00
    Forward
    2.94
     FORWARD
    2.86
     forwards
    2.56
    FORWARD
    2.53
     forwarding
    2.14
     onward
    2.03
     fwd
    2.02
    Activations Density 0.530%

    No Known Activations