© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13707
    Prev
    Next
    INDEX
    Explanations

    concepts related to requirements, actions, and procedures for achieving goals

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

    Infinitive verbs appearing after "to"

    np_acts-logits-general · gemini-2.0-flash

    successful actions and outcomes

    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
     esternos
    -0.63
     GenerationType
    -0.59
     ModelExpression
    -0.57
     TestBed
    -0.54
     kaynağından
    -0.54
    IBOutlet
    -0.54
    ::_('
    -0.54
    EndContext
    -0.53
    Captor
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    POSITIVE LOGITS
     successfully
    1.28
     successful
    1.28
     Successful
    1.12
     effective
    1.11
     properly
    1.11
    successful
    1.11
    Successful
    1.05
     Successfully
    1.05
     success
    1.05
    successfully
    1.03
    Activations Density 0.425%

    No Known Activations