© 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. 18-GEMMASCOPE-RES-16K
    11. 1774
    Prev
    Next
    INDEX
    Explanations

    expressions of choices and consequences in personal or moral contexts

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

    Reflexive pronouns

    np_acts-logits-general · gemini-2.0-flash

    reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.66
     ViewGroup
    -0.56
    ViewGroup
    -0.53
    
    -0.50
    JAXB
    -0.49
    tagHelperRunner
    -0.49
     TPM
    -0.49
    ,‎
    -0.47
    IContainer
    -0.46
    umman
    -0.45
    POSITIVE LOGITS
     himself
    2.69
     herself
    2.65
     themselves
    2.63
     yourself
    2.61
     ourselves
    2.51
    themselves
    2.37
    himself
    2.33
     myself
    2.33
     itself
    2.32
     oneself
    2.31
    Activations Density 0.305%

    No Known Activations