Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10262
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate movement or progression

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

    "go"

    np_acts-logits-general · gemini-2.0-flash

    went on, went through, went to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انيف
    -0.66
    >>()
    -0.60
     TextInputType
    -0.59
    IsPostBack
    -0.58
    XmlAccessType
    -0.58
    HasAnnotation
    -0.53
    ίων
    -0.53
    jsonwebtoken
    -0.51
     Sense
    -0.51
    IBOutlet
    -0.50
    POSITIVE LOGITS
     goes
    0.66
     went
    0.64
     Goes
    0.61
     Went
    0.59
     going
    0.59
    ctez
    0.57
     go
    0.57
    Went
    0.54
    Goes
    0.54
    went
    0.53
    Activations Density 0.088%

    No Known Activations