© 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. 28-GEMMASCOPE-RES-16K
    11. 4207
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to change, adaptation, and transformation in various contexts

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

    Verbs indicating a change of state or position

    np_acts-logits-general · gemini-2.0-flash

    change of state or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.47
    __":
    -0.46
    MENAFN
    -0.38
    хьтан
    -0.38
     externi
    -0.37
     Италијани
    -0.37
     gynhyrchwyd
    -0.36
     postIndex
    -0.34
    stdc
    -0.34
    ETHING
    -0.32
    POSITIVE LOGITS
     ashore
    0.58
     oneself
    0.56
     sebou
    0.54
     yourself
    0.54
     yourselves
    0.54
    themselves
    0.52
     themselves
    0.52
     sobą
    0.52
     into
    0.52
     ourselves
    0.51
    Activations Density 0.345%

    No Known Activations